{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/reinforcement-learning-1/papers/ran/8","list_of":"/task/reinforcement-learning-1","task":"Reinforcement Learning (RL)","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":8,"pages_in_order":15,"rows_per_page":100,"rows":[701,800],"of":1416,"counts":{"archive_papers_tagged":15113,"with_a_code_link":4749,"where_syntology_ran_a_sample":1416,"not_listed_spam_title":0,"listed":15113,"listed_where_code_ran":1416,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1186,"every_run_a_failure_of_syntologys_instrument":230,"listed_with_a_run_with_no_instrument_failure":1186,"listed_every_run_a_failure_of_syntologys_instrument":230,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/reinforcement-learning-1/papers/ran/1","prev":"/task/reinforcement-learning-1/papers/ran/7","next":"/task/reinforcement-learning-1/papers/ran/9","papers":[{"url":"/paper/the-shapley-value-in-machine-learning","slug":"the-shapley-value-in-machine-learning","title":"The Shapley Value in Machine Learning","date":"2022-02-11","arxiv_id":"2202.05594","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-shapley-value-in-machine-learning#ran","syntology_url":"https://syntology.ai/paper/2202.05594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.05594"}},"official":{"repos":["benedekrozemberczki/shapley"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/online-decision-transformer","slug":"online-decision-transformer","title":"Online Decision Transformer","date":"2022-02-11","arxiv_id":"2202.05607","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/online-decision-transformer#ran","syntology_url":"https://syntology.ai/paper/2202.05607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.05607"}},"official":{"repos":["facebookresearch/online-dt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"url":"/paper/rethinking-goal-conditioned-supervised-1","slug":"rethinking-goal-conditioned-supervised-1","title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","date":"2022-02-09","arxiv_id":"2202.04478","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rethinking-goal-conditioned-supervised-1#ran","syntology_url":"https://syntology.ai/paper/2202.04478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04478"}},"official":{"repos":["yangrui2015/awgcsl"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/contextualize-me-the-case-for-context-in","slug":"contextualize-me-the-case-for-context-in","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","date":"2022-02-09","arxiv_id":"2202.04500","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/contextualize-me-the-case-for-context-in#ran","syntology_url":"https://syntology.ai/paper/2202.04500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04500"}},"official":{"repos":["automl/CARL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-with-sparse-rewards-1","slug":"reinforcement-learning-with-sparse-rewards-1","title":"Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration","date":"2022-02-09","arxiv_id":"2202.04628","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-learning-with-sparse-rewards-1#ran","syntology_url":"https://syntology.ai/paper/2202.04628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04628"}},"official":{"repos":["desikrengarajan/logo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bayesian-nonparametrics-for-offline-skill","slug":"bayesian-nonparametrics-for-offline-skill","title":"Bayesian Nonparametrics for Offline Skill Discovery","date":"2022-02-09","arxiv_id":"2202.04675","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bayesian-nonparametrics-for-offline-skill#ran","syntology_url":"https://syntology.ai/paper/2202.04675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04675"}},"official":{"repos":["layer6ai-labs/bnpo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/approximating-gradients-for-differentiable","slug":"approximating-gradients-for-differentiable","title":"Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning","date":"2022-02-08","arxiv_id":"2202.03666","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/approximating-gradients-for-differentiable#ran","syntology_url":"https://syntology.ai/paper/2202.03666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03666"}},"official":{"repos":["icaros-usc/dqd-rl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-synthetic-environments-and-reward-1","slug":"learning-synthetic-environments-and-reward-1","title":"Learning Synthetic Environments and Reward Networks for Reinforcement Learning","date":"2022-02-06","arxiv_id":"2202.02790","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-synthetic-environments-and-reward-1#ran","syntology_url":"https://syntology.ai/paper/2202.02790","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.02790"}},"official":{"repos":["automl/learning_environments"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarially-trained-actor-critic-for","slug":"adversarially-trained-actor-critic-for","title":"Adversarially Trained Actor Critic for Offline Reinforcement Learning","date":"2022-02-05","arxiv_id":"2202.02446","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarially-trained-actor-critic-for#ran","syntology_url":"https://syntology.ai/paper/2202.02446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.02446"}},"official":{"repos":["microsoft/atac"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/smodice-versatile-offline-imitation-learning","slug":"smodice-versatile-offline-imitation-learning","title":"Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching","date":"2022-02-04","arxiv_id":"2202.02433","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":4,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/smodice-versatile-offline-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2202.02433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.02433"}},"official":{"repos":["jasonma2016/smodice"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cic-contrastive-intrinsic-control-for-1","slug":"cic-contrastive-intrinsic-control-for-1","title":"CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery","date":"2022-02-01","arxiv_id":"2202.00161","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cic-contrastive-intrinsic-control-for-1#ran","syntology_url":"https://syntology.ai/paper/2202.00161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.00161"}},"official":null}},{"url":"/paper/dns-determinantal-point-process-based-neural","slug":"dns-determinantal-point-process-based-neural","title":"DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning","date":"2022-01-31","arxiv_id":"2201.13357","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dns-determinantal-point-process-based-neural#ran","syntology_url":"https://syntology.ai/paper/2201.13357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.13357"}},"official":{"repos":["IntelLabs/DNS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/don-t-change-the-algorithm-change-the-data","slug":"don-t-change-the-algorithm-change-the-data","title":"Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning","date":"2022-01-31","arxiv_id":"2201.13425","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/don-t-change-the-algorithm-change-the-data#ran","syntology_url":"https://syntology.ai/paper/2201.13425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.13425"}},"official":{"repos":["denisyarats/exorl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/explaining-reinforcement-learning-policies","slug":"explaining-reinforcement-learning-policies","title":"Explaining Reinforcement Learning Policies through Counterfactual Trajectories","date":"2022-01-29","arxiv_id":"2201.12462","repositories_listed":1,"syntology":{"n":11,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":11,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/explaining-reinforcement-learning-policies#ran","syntology_url":"https://syntology.ai/paper/2201.12462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12462"}},"official":{"repos":["juliusfrost/cfrl-rllib"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/constrained-variational-policy-optimization","slug":"constrained-variational-policy-optimization","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","date":"2022-01-28","arxiv_id":"2201.11927","repositories_listed":2,"syntology":{"n":11,"n_ran":5,"n_constructed":2,"n_ran_checked":2,"n_instrument":3,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/constrained-variational-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/2201.11927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11927"}},"official":{"repos":["liuzuxin/cvpo-safe-rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mask-based-latent-reconstruction-for","slug":"mask-based-latent-reconstruction-for","title":"Mask-based Latent Reconstruction for Reinforcement Learning","date":"2022-01-28","arxiv_id":"2201.12096","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":4,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mask-based-latent-reconstruction-for#ran","syntology_url":"https://syntology.ai/paper/2201.12096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12096"}},"official":{"repos":["microsoft/Mask-based-Latent-Reconstruction"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/can-wikipedia-help-offline-reinforcement","slug":"can-wikipedia-help-offline-reinforcement","title":"Can Wikipedia Help Offline Reinforcement Learning?","date":"2022-01-28","arxiv_id":"2201.12122","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-wikipedia-help-offline-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2201.12122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12122"}},"official":{"repos":["machelreid/can-wikipedia-help-offline-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-safe-reinforcement-learning-with-a","slug":"towards-safe-reinforcement-learning-with-a","title":"Towards Safe Reinforcement Learning with a Safety Editor Policy","date":"2022-01-28","arxiv_id":"2201.12427","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-safe-reinforcement-learning-with-a#ran","syntology_url":"https://syntology.ai/paper/2201.12427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12427"}},"official":{"repos":["hnyu/seditor"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/exploration-with-a-finite-brain","slug":"exploration-with-a-finite-brain","title":"Modeling Human Exploration Through Resource-Rational Reinforcement Learning","date":"2022-01-27","arxiv_id":"2201.11817","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exploration-with-a-finite-brain#ran","syntology_url":"https://syntology.ai/paper/2201.11817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11817"}},"official":{"repos":["marcelbinz/resource-rational-reinforcement-learning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/constrained-policy-optimization-via-bayesian-1","slug":"constrained-policy-optimization-via-bayesian-1","title":"Constrained Policy Optimization via Bayesian World Models","date":"2022-01-24","arxiv_id":"2201.09802","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/constrained-policy-optimization-via-bayesian-1#ran","syntology_url":"https://syntology.ai/paper/2201.09802","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.09802"}},"official":{"repos":["yardenas/la-mbda"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/environment-generation-for-zero-shot-1","slug":"environment-generation-for-zero-shot-1","title":"Environment Generation for Zero-Shot Compositional Reinforcement Learning","date":"2022-01-21","arxiv_id":"2201.08896","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/environment-generation-for-zero-shot-1#ran","syntology_url":"https://syntology.ai/paper/2201.08896","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.08896"}},"official":{"repos":["google-research/google-research"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-efficient-deep-reinforcement-learning-5","slug":"sample-efficient-deep-reinforcement-learning-5","title":"Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation","date":"2022-01-05","arxiv_id":"2201.01666","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sample-efficient-deep-reinforcement-learning-5#ran","syntology_url":"https://syntology.ai/paper/2201.01666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.01666"}},"official":{"repos":["montrealrobotics/iv_rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/settling-the-bias-and-variance-of-meta","slug":"settling-the-bias-and-variance-of-meta","title":"A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning","date":"2021-12-31","arxiv_id":"2112.15400","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/settling-the-bias-and-variance-of-meta#ran","syntology_url":"https://syntology.ai/paper/2112.15400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.15400"}},"official":{"repos":["Benjamin-eecs/Theoretical-GMRL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/moral-aligning-ai-with-human-norms-through","slug":"moral-aligning-ai-with-human-norms-through","title":"MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning","date":"2021-12-30","arxiv_id":"2201.00012","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/moral-aligning-ai-with-human-norms-through#ran","syntology_url":"https://syntology.ai/paper/2201.00012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00012"}},"official":{"repos":["mlpeschl/moral_rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exponential-family-model-based-reinforcement","slug":"exponential-family-model-based-reinforcement","title":"Exponential Family Model-Based Reinforcement Learning via Score Matching","date":"2021-12-28","arxiv_id":"2112.14195","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/exponential-family-model-based-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2112.14195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.14195"}},"official":{"repos":["anmolkabra/score-matching-rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-with-dynamic-convex","slug":"reinforcement-learning-with-dynamic-convex","title":"Reinforcement Learning with Dynamic Convex Risk Measures","date":"2021-12-26","arxiv_id":"2112.13414","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-learning-with-dynamic-convex#ran","syntology_url":"https://syntology.ai/paper/2112.13414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.13414"}},"official":{"repos":["acoache/rl-dynamicconvexrisk"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/differentially-private-regret-minimization-in","slug":"differentially-private-regret-minimization-in","title":"Differentially Private Regret Minimization in Episodic Markov Decision Processes","date":"2021-12-20","arxiv_id":"2112.10599","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/differentially-private-regret-minimization-in#ran","syntology_url":"https://syntology.ai/paper/2112.10599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.10599"}},"official":{"repos":["xingyuzhou989/privatetabularrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/autonomous-reinforcement-learning-formalism-1","slug":"autonomous-reinforcement-learning-formalism-1","title":"Autonomous Reinforcement Learning: Formalism and Benchmarking","date":"2021-12-17","arxiv_id":"2112.09605","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/autonomous-reinforcement-learning-formalism-1#ran","syntology_url":"https://syntology.ai/paper/2112.09605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.09605"}},"official":{"repos":["architsharma97/earl_benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-reinforcement-learning-in","slug":"unsupervised-reinforcement-learning-in","title":"Unsupervised Reinforcement Learning in Multiple Environments","date":"2021-12-16","arxiv_id":"2112.08746","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-reinforcement-learning-in#ran","syntology_url":"https://syntology.ai/paper/2112.08746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.08746"}},"official":{"repos":["muttimirco/alphamepol"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/finrl-meta-a-universe-of-near-real-market","slug":"finrl-meta-a-universe-of-near-real-market","title":"FinRL-Meta: A Universe of Near-Real Market Environments for Data-Driven Deep Reinforcement Learning in Quantitative Finance","date":"2021-12-13","arxiv_id":"2112.06753","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/finrl-meta-a-universe-of-near-real-market#ran","syntology_url":"https://syntology.ai/paper/2112.06753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.06753"}},"official":{"repos":["ai4finance-foundation/finrl-meta"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pantheonrl-a-marl-library-for-dynamic","slug":"pantheonrl-a-marl-library-for-dynamic","title":"PantheonRL: A MARL Library for Dynamic Training Interactions","date":"2021-12-13","arxiv_id":"2112.07013","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pantheonrl-a-marl-library-for-dynamic#ran","syntology_url":"https://syntology.ai/paper/2112.07013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.07013"}},"official":{"repos":["Stanford-ILIAD/PantheonRL"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/human-level-control-through-directly-trained","slug":"human-level-control-through-directly-trained","title":"Human-Level Control through Directly-Trained Deep Spiking Q-Networks","date":"2021-12-13","arxiv_id":"2201.07211","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/human-level-control-through-directly-trained#ran","syntology_url":"https://syntology.ai/paper/2201.07211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.07211"}},"official":{"repos":["aptx395/deep-spiking-q-networks"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/elegantrl-podracer-scalable-and-elastic","slug":"elegantrl-podracer-scalable-and-elastic","title":"ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learning","date":"2021-12-11","arxiv_id":"2112.05923","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/elegantrl-podracer-scalable-and-elastic#ran","syntology_url":"https://syntology.ai/paper/2112.05923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05923"}},"official":{"repos":["ai4finance-foundation/elegantrl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-q-network-with-proximal-iteration-1","slug":"deep-q-network-with-proximal-iteration-1","title":"Faster Deep Reinforcement Learning with Slower Online Network","date":"2021-12-10","arxiv_id":"2112.05848","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-q-network-with-proximal-iteration-1#ran","syntology_url":"https://syntology.ai/paper/2112.05848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05848"}},"official":{"repos":["amazon-research/fast-rl-with-slow-updates"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/an-experimental-design-perspective-on-model","slug":"an-experimental-design-perspective-on-model","title":"An Experimental Design Perspective on Model-Based Reinforcement Learning","date":"2021-12-09","arxiv_id":"2112.05244","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-experimental-design-perspective-on-model#ran","syntology_url":"https://syntology.ai/paper/2112.05244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05244"}},"official":null}},{"url":"/paper/godot-reinforcement-learning-agents","slug":"godot-reinforcement-learning-agents","title":"Godot Reinforcement Learning Agents","date":"2021-12-07","arxiv_id":"2112.03636","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/godot-reinforcement-learning-agents#ran","syntology_url":"https://syntology.ai/paper/2112.03636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03636"}},"official":{"repos":["edbeeching/godot_rl_agents"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/functional-regularization-for-reinforcement-1","slug":"functional-regularization-for-reinforcement-1","title":"Functional Regularization for Reinforcement Learning via Learned Fourier Features","date":"2021-12-06","arxiv_id":"2112.03257","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/functional-regularization-for-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2112.03257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03257"}},"official":{"repos":["alexlioralexli/learned-fourier-features"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-complexity-of-robust-reinforcement","slug":"sample-complexity-of-robust-reinforcement","title":"Sample Complexity of Robust Reinforcement Learning with a Generative Model","date":"2021-12-02","arxiv_id":"2112.01506","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sample-complexity-of-robust-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2112.01506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01506"}},"official":{"repos":["kishanpb/RobustRL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-on-policy-data-collection-for-data","slug":"robust-on-policy-data-collection-for-data","title":"Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning","date":"2021-11-29","arxiv_id":"2111.14552","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-on-policy-data-collection-for-data#ran","syntology_url":"https://syntology.ai/paper/2111.14552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14552"}},"official":{"repos":["uoe-agents/robust_onpolicy_data_collection"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-long-term-reward-redistribution-via-1","slug":"learning-long-term-reward-redistribution-via-1","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","date":"2021-11-26","arxiv_id":"2111.13485","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-long-term-reward-redistribution-via-1#ran","syntology_url":"https://syntology.ai/paper/2111.13485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.13485"}},"official":{"repos":["stilwell-git/randomized-return-decomposition"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptively-calibrated-critic-estimates-for","slug":"adaptively-calibrated-critic-estimates-for","title":"Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning","date":"2021-11-24","arxiv_id":"2111.12673","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptively-calibrated-critic-estimates-for#ran","syntology_url":"https://syntology.ai/paper/2111.12673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12673"}},"official":{"repos":["nicolinho/acc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/off-policy-correction-for-multi-agent","slug":"off-policy-correction-for-multi-agent","title":"Off-Policy Correction For Multi-Agent Reinforcement Learning","date":"2021-11-22","arxiv_id":"2111.11229","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/off-policy-correction-for-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2111.11229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.11229"}},"official":{"repos":["awarelab/seed_rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generalized-decision-transformer-for-offline","slug":"generalized-decision-transformer-for-offline","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","date":"2021-11-19","arxiv_id":"2111.10364","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalized-decision-transformer-for-offline#ran","syntology_url":"https://syntology.ai/paper/2111.10364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.10364"}},"official":{"repos":["frt03/generalized_dt"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/successor-feature-landmarks-for-long-horizon","slug":"successor-feature-landmarks-for-long-horizon","title":"Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning","date":"2021-11-18","arxiv_id":"2111.09858","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/successor-feature-landmarks-for-long-horizon#ran","syntology_url":"https://syntology.ai/paper/2111.09858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09858"}},"official":null}},{"url":"/paper/cleanrl-high-quality-single-file","slug":"cleanrl-high-quality-single-file","title":"CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms","date":"2021-11-16","arxiv_id":"2111.08819","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cleanrl-high-quality-single-file#ran","syntology_url":"https://syntology.ai/paper/2111.08819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.08819"}},"official":{"repos":["vwxyzjn/cleanrl"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/joint-synthesis-of-safety-certificate-and","slug":"joint-synthesis-of-safety-certificate-and","title":"Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning","date":"2021-11-15","arxiv_id":"2111.07695","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/joint-synthesis-of-safety-certificate-and#ran","syntology_url":"https://syntology.ai/paper/2111.07695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.07695"}},"official":{"repos":["mahaitongdae/safety_index_synthesis"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/powergridworld-a-framework-for-multi-agent","slug":"powergridworld-a-framework-for-multi-agent","title":"PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems","date":"2021-11-10","arxiv_id":"2111.05969","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/powergridworld-a-framework-for-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2111.05969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.05969"}},"official":{"repos":["nrel/powergridworld"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-policy-optimization-with-local","slug":"safe-policy-optimization-with-local","title":"Safe Policy Optimization with Local Generalized Linear Function Approximations","date":"2021-11-09","arxiv_id":"2111.04894","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-policy-optimization-with-local#ran","syntology_url":"https://syntology.ai/paper/2111.04894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.04894"}},"official":{"repos":["akifumi-wachi-4/spolf"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rlds-an-ecosystem-to-generate-share-and-use","slug":"rlds-an-ecosystem-to-generate-share-and-use","title":"RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning","date":"2021-11-04","arxiv_id":"2111.02767","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rlds-an-ecosystem-to-generate-share-and-use#ran","syntology_url":"https://syntology.ai/paper/2111.02767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02767"}},"official":{"repos":["google-research/rlds"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/b-pref-benchmarking-preference-based","slug":"b-pref-benchmarking-preference-based","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","date":"2021-11-04","arxiv_id":"2111.03026","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/b-pref-benchmarking-preference-based#ran","syntology_url":"https://syntology.ai/paper/2111.03026","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03026"}},"official":{"repos":["rll-research/b-pref"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/infinite-time-horizon-safety-of-bayesian","slug":"infinite-time-horizon-safety-of-bayesian","title":"Infinite Time Horizon Safety of Bayesian Neural Networks","date":"2021-11-04","arxiv_id":"2111.03165","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/infinite-time-horizon-safety-of-bayesian#ran","syntology_url":"https://syntology.ai/paper/2111.03165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03165"}},"official":{"repos":["mlech26l/bayesian_nn_safety"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/curriculum-offline-imitation-learning","slug":"curriculum-offline-imitation-learning","title":"Curriculum Offline Imitation Learning","date":"2021-11-03","arxiv_id":"2111.02056","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/curriculum-offline-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2111.02056","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02056"}},"official":{"repos":["apexrl/coil"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-large-neighborhood-search-policy-for","slug":"learning-large-neighborhood-search-policy-for","title":"Learning Large Neighborhood Search Policy for Integer Programming","date":"2021-11-01","arxiv_id":"2111.03466","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-large-neighborhood-search-policy-for#ran","syntology_url":"https://syntology.ai/paper/2111.03466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03466"}},"official":{"repos":["wxy1427/learn-lns-policy"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/context-meta-reinforcement-learning-via","slug":"context-meta-reinforcement-learning-via","title":"Context Meta-Reinforcement Learning via Neuromodulation","date":"2021-10-30","arxiv_id":"2111.00134","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/context-meta-reinforcement-learning-via#ran","syntology_url":"https://syntology.ai/paper/2111.00134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00134"}},"official":{"repos":["dlpbc/nm-metarl","soltoggio/ct-graph"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-joint-learning-for-solving-placement-and","slug":"on-joint-learning-for-solving-placement-and","title":"On Joint Learning for Solving Placement and Routing in Chip Design","date":"2021-10-30","arxiv_id":"2111.00234","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-joint-learning-for-solving-placement-and#ran","syntology_url":"https://syntology.ai/paper/2111.00234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00234"}},"official":{"repos":["thinklab-sjtu/eda-ai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/proximal-reinforcement-learning-efficient-off","slug":"proximal-reinforcement-learning-efficient-off","title":"Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes","date":"2021-10-28","arxiv_id":"2110.15332","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/proximal-reinforcement-learning-efficient-off#ran","syntology_url":"https://syntology.ai/paper/2110.15332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15332"}},"official":{"repos":["causalml/proximalrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dreamerpro-reconstruction-free-model-based-1","slug":"dreamerpro-reconstruction-free-model-based-1","title":"DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations","date":"2021-10-27","arxiv_id":"2110.14565","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dreamerpro-reconstruction-free-model-based-1#ran","syntology_url":"https://syntology.ai/paper/2110.14565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14565"}},"official":{"repos":["fdeng18/dreamer-pro"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/landmark-guided-subgoal-generation-in","slug":"landmark-guided-subgoal-generation-in","title":"Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning","date":"2021-10-26","arxiv_id":"2110.13625","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/landmark-guided-subgoal-generation-in#ran","syntology_url":"https://syntology.ai/paper/2110.13625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13625"}},"official":{"repos":["junsu-kim97/higl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-simulate-self-driven-particles","slug":"learning-to-simulate-self-driven-particles","title":"Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization","date":"2021-10-26","arxiv_id":"2110.13827","repositories_listed":1,"syntology":{"n":7,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/learning-to-simulate-self-driven-particles#ran","syntology_url":"https://syntology.ai/paper/2110.13827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13827"}},"official":{"repos":["decisionforce/CoPO"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/fault-tolerant-federated-reinforcement","slug":"fault-tolerant-federated-reinforcement","title":"Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee","date":"2021-10-26","arxiv_id":"2110.14074","repositories_listed":2,"syntology":{"n":15,"n_ran":9,"n_constructed":3,"n_ran_checked":4,"n_instrument":5,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":15,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/fault-tolerant-federated-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2110.14074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14074"}},"official":{"repos":["flint-xf-fan/Byzantine-Federeated-RL"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/goal-aware-cross-entropy-for-multi-target","slug":"goal-aware-cross-entropy-for-multi-target","title":"Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning","date":"2021-10-25","arxiv_id":"2110.12985","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/goal-aware-cross-entropy-for-multi-target#ran","syntology_url":"https://syntology.ai/paper/2110.12985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.12985"}},"official":{"repos":["kibeomkim/gace-gdan"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-skills-for-efficient-exploration","slug":"hierarchical-skills-for-efficient-exploration","title":"Hierarchical Skills for Efficient Exploration","date":"2021-10-20","arxiv_id":"2110.10809","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hierarchical-skills-for-efficient-exploration#ran","syntology_url":"https://syntology.ai/paper/2110.10809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.10809"}},"official":{"repos":["facebookresearch/hsd3"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastive-active-inference","slug":"contrastive-active-inference","title":"Contrastive Active Inference","date":"2021-10-19","arxiv_id":"2110.10083","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":2,"n_ran_checked":2,"n_instrument":7,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"9 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/contrastive-active-inference#ran","syntology_url":"https://syntology.ai/paper/2110.10083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.10083"}},"official":{"repos":["mazpie/contrastive-aif"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-driving-via-expert-guided-policy","slug":"safe-driving-via-expert-guided-policy","title":"Safe Driving via Expert Guided Policy Optimization","date":"2021-10-13","arxiv_id":"2110.06831","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/safe-driving-via-expert-guided-policy#ran","syntology_url":"https://syntology.ai/paper/2110.06831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06831"}},"official":{"repos":["decisionforce/EGPO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-reinforcement-learning-with-implicit","slug":"offline-reinforcement-learning-with-implicit","title":"Offline Reinforcement Learning with Implicit Q-Learning","date":"2021-10-12","arxiv_id":"2110.06169","repositories_listed":17,"syntology":{"n":58,"n_ran":45,"n_constructed":23,"n_ran_checked":37,"n_instrument":8,"n_unverified":13,"n_honours":0,"n_violates":0,"n_no_contract":37,"n_pointer_only":23,"phrase":"45 ran (of which 23 constructed an object rather than computing a result; 37 with no instrument failure: 0 honoured, 0 violated, 37 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/offline-reinforcement-learning-with-implicit#ran","syntology_url":"https://syntology.ai/paper/2110.06169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06169"}},"official":{"repos":["rail-berkeley/rlkit","ikostrikov/implicit_q_learning"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/beyond-pick-and-place-tackling-robotic","slug":"beyond-pick-and-place-tackling-robotic","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","date":"2021-10-12","arxiv_id":"2110.06192","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/beyond-pick-and-place-tackling-robotic#ran","syntology_url":"https://syntology.ai/paper/2110.06192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06192"}},"official":{"repos":["deepmind/rgb_stacking"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/starformer-transformer-with-state-action-1","slug":"starformer-transformer-with-state-action-1","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","date":"2021-10-12","arxiv_id":"2110.06206","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/starformer-transformer-with-state-action-1#ran","syntology_url":"https://syntology.ai/paper/2110.06206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06206"}},"official":{"repos":["elicassion/StARformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-temporally-consistent-1","slug":"learning-temporally-consistent-1","title":"Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning","date":"2021-10-11","arxiv_id":"2110.04935","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-temporally-consistent-1#ran","syntology_url":"https://syntology.ai/paper/2110.04935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04935"}},"official":{"repos":["anon-researcher-repo/ksl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-closer-look-at-advantage-filtered","slug":"a-closer-look-at-advantage-filtered","title":"A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets","date":"2021-10-10","arxiv_id":"2110.04698","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-closer-look-at-advantage-filtered#ran","syntology_url":"https://syntology.ai/paper/2110.04698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04698"}},"official":{"repos":["jakegrigsby/cc-afbc","jakegrigsby/deep_control","jakegrigsby/super_sac"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/augmenting-reinforcement-learning-with","slug":"augmenting-reinforcement-learning-with","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","date":"2021-10-07","arxiv_id":"2110.03655","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/augmenting-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2110.03655","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03655"}},"official":{"repos":["UT-Austin-RPL/maple"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/replay-guided-adversarial-environment-design","slug":"replay-guided-adversarial-environment-design","title":"Replay-Guided Adversarial Environment Design","date":"2021-10-06","arxiv_id":"2110.02439","repositories_listed":4,"syntology":{"n":4,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/replay-guided-adversarial-environment-design#ran","syntology_url":"https://syntology.ai/paper/2110.02439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02439"}},"official":null}},{"url":"/paper/multi-agent-constrained-policy-optimisation","slug":"multi-agent-constrained-policy-optimisation","title":"Multi-Agent Constrained Policy Optimisation","date":"2021-10-06","arxiv_id":"2110.02793","repositories_listed":4,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-agent-constrained-policy-optimisation#ran","syntology_url":"https://syntology.ai/paper/2110.02793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02793"}},"official":{"repos":["chauncygu/multi-agent-constrained-policy-optimisation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/dropout-q-functions-for-doubly-efficient","slug":"dropout-q-functions-for-doubly-efficient","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","date":"2021-10-05","arxiv_id":"2110.02034","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":3,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dropout-q-functions-for-doubly-efficient#ran","syntology_url":"https://syntology.ai/paper/2110.02034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02034"}},"official":{"repos":["TakuyaHiraoka/Dropout-Q-Functions-for-Doubly-Efficient-Reinforcement-Learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/hit-and-lead-discovery-with-explorative-rl","slug":"hit-and-lead-discovery-with-explorative-rl","title":"Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation","date":"2021-10-04","arxiv_id":"2110.01219","repositories_listed":0,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hit-and-lead-discovery-with-explorative-rl#ran","syntology_url":"https://syntology.ai/paper/2110.01219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01219"}},"official":null}},{"url":"/paper/large-batch-experience-replay","slug":"large-batch-experience-replay","title":"Large Batch Experience Replay","date":"2021-10-04","arxiv_id":"2110.01528","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_constructed":4,"n_ran_checked":4,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/large-batch-experience-replay#ran","syntology_url":"https://syntology.ai/paper/2110.01528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01528"}},"official":{"repos":["sureli/laber"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/uncertainty-based-offline-reinforcement","slug":"uncertainty-based-offline-reinforcement","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","date":"2021-10-04","arxiv_id":"2110.01548","repositories_listed":5,"syntology":{"n":21,"n_ran":13,"n_constructed":11,"n_ran_checked":12,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":6,"phrase":"13 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/uncertainty-based-offline-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2110.01548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01548"}},"official":null}},{"url":"/paper/a-cramer-distance-perspective-on-non-crossing","slug":"a-cramer-distance-perspective-on-non-crossing","title":"A Cramér Distance perspective on Quantile Regression based Distributional Reinforcement Learning","date":"2021-10-01","arxiv_id":"2110.00535","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-cramer-distance-perspective-on-non-crossing#ran","syntology_url":"https://syntology.ai/paper/2110.00535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00535"}},"official":{"repos":["alherit/cr-dqn"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unified-data-collection-for-visual-inertial","slug":"unified-data-collection-for-visual-inertial","title":"Unified Data Collection for Visual-Inertial Calibration via Deep Reinforcement Learning","date":"2021-09-30","arxiv_id":"2109.14974","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unified-data-collection-for-visual-inertial#ran","syntology_url":"https://syntology.ai/paper/2109.14974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.14974"}},"official":{"repos":["ethz-asl/Learn-to-Calibrate"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/real-robot-challenge-using-deep-reinforcement","slug":"real-robot-challenge-using-deep-reinforcement","title":"Solving the Real Robot Challenge using Deep Reinforcement Learning","date":"2021-09-30","arxiv_id":"2109.15233","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/real-robot-challenge-using-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2109.15233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.15233"}},"official":{"repos":["robertmccarthy97/rrc_phase1"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/width-based-planning-and-active-learning-for","slug":"width-based-planning-and-active-learning-for","title":"Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari","date":"2021-09-30","arxiv_id":"2109.15310","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/width-based-planning-and-active-learning-for#ran","syntology_url":"https://syntology.ai/paper/2109.15310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.15310"}},"official":{"repos":["ibm/atari-active-learning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/stackelberg-actor-critic-game-theoretic","slug":"stackelberg-actor-critic-game-theoretic","title":"Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms","date":"2021-09-25","arxiv_id":"2109.12286","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/stackelberg-actor-critic-game-theoretic#ran","syntology_url":"https://syntology.ai/paper/2109.12286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.12286"}},"official":{"repos":["leozhengzly/stackelberg-actor-critic-algos"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/trust-region-policy-optimisation-in-multi","slug":"trust-region-policy-optimisation-in-multi","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","date":"2021-09-23","arxiv_id":"2109.11251","repositories_listed":11,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/trust-region-policy-optimisation-in-multi#ran","syntology_url":"https://syntology.ai/paper/2109.11251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11251"}},"official":{"repos":["cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning","anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-workflow-for-offline-model-free-robotic","slug":"a-workflow-for-offline-model-free-robotic","title":"A Workflow for Offline Model-Free Robotic Reinforcement Learning","date":"2021-09-22","arxiv_id":"2109.10813","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-workflow-for-offline-model-free-robotic#ran","syntology_url":"https://syntology.ai/paper/2109.10813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10813"}},"official":null}},{"url":"/paper/generalization-in-text-based-games-via","slug":"generalization-in-text-based-games-via","title":"Generalization in Text-based Games via Hierarchical Reinforcement Learning","date":"2021-09-21","arxiv_id":"2109.09968","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalization-in-text-based-games-via#ran","syntology_url":"https://syntology.ai/paper/2109.09968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.09968"}},"official":{"repos":["yunqiuxu/h-kga"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hindsight-foresight-relabeling-for-meta","slug":"hindsight-foresight-relabeling-for-meta","title":"Hindsight Foresight Relabeling for Meta-Reinforcement Learning","date":"2021-09-18","arxiv_id":"2109.09031","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hindsight-foresight-relabeling-for-meta#ran","syntology_url":"https://syntology.ai/paper/2109.09031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.09031"}},"official":{"repos":["michaelwan11/hfr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/balancing-detectability-and-performance-of","slug":"balancing-detectability-and-performance-of","title":"Balancing detectability and performance of attacks on the control channel of Markov Decision Processes","date":"2021-09-15","arxiv_id":"2109.07171","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/balancing-detectability-and-performance-of#ran","syntology_url":"https://syntology.ai/paper/2109.07171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.07171"}},"official":{"repos":["rssalessio/optimal-attack-control-channel-mdp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/gradient-imitation-reinforcement-learning-for","slug":"gradient-imitation-reinforcement-learning-for","title":"Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction","date":"2021-09-14","arxiv_id":"2109.06415","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gradient-imitation-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2109.06415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06415"}},"official":{"repos":["thu-bpm/gradlre"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-control-gym-a-unified-benchmark-suite","slug":"safe-control-gym-a-unified-benchmark-suite","title":"safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics","date":"2021-09-13","arxiv_id":"2109.06325","repositories_listed":4,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/safe-control-gym-a-unified-benchmark-suite#ran","syntology_url":"https://syntology.ai/paper/2109.06325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06325"}},"official":{"repos":["utiasDSL/safe-control-gym"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/hyar-addressing-discrete-continuous-action","slug":"hyar-addressing-discrete-continuous-action","title":"HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation","date":"2021-09-12","arxiv_id":"2109.05490","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","sample_list":"/paper/hyar-addressing-discrete-continuous-action#ran","syntology_url":"https://syntology.ai/paper/2109.05490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05490"}},"official":null}},{"url":"/paper/physics-based-deep-learning","slug":"physics-based-deep-learning","title":"Physics-based Deep Learning","date":"2021-09-11","arxiv_id":"2109.05237","repositories_listed":6,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/physics-based-deep-learning#ran","syntology_url":"https://syntology.ai/paper/2109.05237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05237"}},"official":{"repos":["thunil/Physics-Based-Deep-Learning","tum-pbs/PhiFlow","tum-pbs/diffusion-based-flow-prediction","tum-pbs/pbdl-dataset","tum-pbs/pbdl-book"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["named_in_paper","official"]}}},{"url":"/paper/timetraveler-reinforcement-learning-for","slug":"timetraveler-reinforcement-learning-for","title":"TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting","date":"2021-09-09","arxiv_id":"2109.04101","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/timetraveler-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2109.04101","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04101"}},"official":{"repos":["jhl-hust/titer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/opirl-sample-efficient-off-policy-inverse","slug":"opirl-sample-efficient-off-policy-inverse","title":"OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching","date":"2021-09-09","arxiv_id":"2109.04307","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/opirl-sample-efficient-off-policy-inverse#ran","syntology_url":"https://syntology.ai/paper/2109.04307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04307"}},"official":{"repos":["sff1019/opirl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/powergym-a-reinforcement-learning-environment","slug":"powergym-a-reinforcement-learning-environment","title":"PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems","date":"2021-09-08","arxiv_id":"2109.03970","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/powergym-a-reinforcement-learning-environment#ran","syntology_url":"https://syntology.ai/paper/2109.03970","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.03970"}},"official":{"repos":["siemens/powergym"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-sensory-neuron-as-a-transformer","slug":"the-sensory-neuron-as-a-transformer","title":"The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning","date":"2021-09-07","arxiv_id":"2109.02869","repositories_listed":3,"syntology":{"n":8,"n_ran":8,"n_constructed":5,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-sensory-neuron-as-a-transformer#ran","syntology_url":"https://syntology.ai/paper/2109.02869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.02869"}},"official":null}},{"url":"/paper/optimizing-quantum-variational-circuits-with","slug":"optimizing-quantum-variational-circuits-with","title":"Optimizing Quantum Variational Circuits with Deep Reinforcement Learning","date":"2021-09-07","arxiv_id":"2109.03188","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/optimizing-quantum-variational-circuits-with#ran","syntology_url":"https://syntology.ai/paper/2109.03188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.03188"}},"official":{"repos":["lockwo/rl_qvc_opt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-predictable-control","slug":"robust-predictable-control","title":"Robust Predictable Control","date":"2021-09-07","arxiv_id":"2109.03214","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-predictable-control#ran","syntology_url":"https://syntology.ai/paper/2109.03214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.03214"}},"official":{"repos":["eleurent/highway-env"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/catastrophic-interference-in-reinforcement","slug":"catastrophic-interference-in-reinforcement","title":"Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation","date":"2021-09-01","arxiv_id":"2109.00525","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/catastrophic-interference-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2109.00525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00525"}},"official":{"repos":["sweety-dm/interference-aware-deep-q-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/warpdrive-extremely-fast-end-to-end-deep","slug":"warpdrive-extremely-fast-end-to-end-deep","title":"WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU","date":"2021-08-31","arxiv_id":"2108.13976","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/warpdrive-extremely-fast-end-to-end-deep#ran","syntology_url":"https://syntology.ai/paper/2108.13976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.13976"}},"official":{"repos":["salesforce/warp-drive"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deep-reinforcement-learning-at-the-edge-of","slug":"deep-reinforcement-learning-at-the-edge-of","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","date":"2021-08-30","arxiv_id":"2108.13264","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":4,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-reinforcement-learning-at-the-edge-of#ran","syntology_url":"https://syntology.ai/paper/2108.13264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.13264"}},"official":{"repos":["google-research/rliable"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/inspecting-the-factuality-of-hallucinated","slug":"inspecting-the-factuality-of-hallucinated","title":"Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization","date":"2021-08-30","arxiv_id":"2109.09784","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/inspecting-the-factuality-of-hallucinated#ran","syntology_url":"https://syntology.ai/paper/2109.09784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.09784"}},"official":{"repos":["mcao516/entfa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"7aafc0c598bb5de89fd0cb8c2078661ebc7b38e54b2a352664d12d6776c2e209","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}