{"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/9","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":9,"pages_in_order":15,"rows_per_page":100,"rows":[801,900],"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/8","next":"/task/reinforcement-learning-1/papers/ran/10","papers":[{"url":"/paper/regen-reinforcement-learning-for-text-and","slug":"regen-reinforcement-learning-for-text-and","title":"ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models","date":"2021-08-27","arxiv_id":"2108.12472","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/regen-reinforcement-learning-for-text-and#ran","syntology_url":"https://syntology.ai/paper/2108.12472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.12472"}},"official":{"repos":["IBM/regen"],"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/end-to-end-urban-driving-by-imitating-a","slug":"end-to-end-urban-driving-by-imitating-a","title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","date":"2021-08-18","arxiv_id":"2108.08265","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-urban-driving-by-imitating-a#ran","syntology_url":"https://syntology.ai/paper/2108.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.08265"}},"official":{"repos":["zhejz/carla-roach"],"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/revisiting-state-augmentation-methods-for","slug":"revisiting-state-augmentation-methods-for","title":"Revisiting State Augmentation methods for Reinforcement Learning with Stochastic Delays","date":"2021-08-17","arxiv_id":"2108.07555","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/revisiting-state-augmentation-methods-for#ran","syntology_url":"https://syntology.ai/paper/2108.07555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07555"}},"official":{"repos":["baranwa2/delayresolvedrl"],"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/imitation-learning-by-reinforcement-learning","slug":"imitation-learning-by-reinforcement-learning","title":"Imitation Learning by Reinforcement Learning","date":"2021-08-10","arxiv_id":"2108.04763","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/imitation-learning-by-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2108.04763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04763"}},"official":{"repos":["spotify-research/il-by-rl"],"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/safe-deep-reinforcement-learning-for-multi","slug":"safe-deep-reinforcement-learning-for-multi","title":"Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces","date":"2021-08-09","arxiv_id":"2108.03952","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/safe-deep-reinforcement-learning-for-multi#ran","syntology_url":"https://syntology.ai/paper/2108.03952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03952"}},"official":{"repos":["zisikons/deep-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/what-matters-in-learning-from-offline-human","slug":"what-matters-in-learning-from-offline-human","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","date":"2021-08-06","arxiv_id":"2108.03298","repositories_listed":1,"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/what-matters-in-learning-from-offline-human#ran","syntology_url":"https://syntology.ai/paper/2108.03298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03298"}},"official":null}},{"url":"/paper/learning-barrier-certificates-towards-safe","slug":"learning-barrier-certificates-towards-safe","title":"Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations","date":"2021-08-04","arxiv_id":"2108.01846","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-barrier-certificates-towards-safe#ran","syntology_url":"https://syntology.ai/paper/2108.01846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.01846"}},"official":{"repos":["roosephu/crabs"],"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":["found_in_text","official"]}}},{"url":"/paper/tianshou-a-highly-modularized-deep","slug":"tianshou-a-highly-modularized-deep","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","date":"2021-07-29","arxiv_id":"2107.14171","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/tianshou-a-highly-modularized-deep#ran","syntology_url":"https://syntology.ai/paper/2107.14171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.14171"}},"official":{"repos":["thu-ml/tianshou"],"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/mastering-visual-continuous-control-improved","slug":"mastering-visual-continuous-control-improved","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","date":"2021-07-20","arxiv_id":"2107.09645","repositories_listed":8,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mastering-visual-continuous-control-improved#ran","syntology_url":"https://syntology.ai/paper/2107.09645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09645"}},"official":{"repos":["facebookresearch/drqv2"],"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/reward-weighted-regression-converges-to-a","slug":"reward-weighted-regression-converges-to-a","title":"Reward-Weighted Regression Converges to a Global Optimum","date":"2021-07-19","arxiv_id":"2107.09088","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/reward-weighted-regression-converges-to-a#ran","syntology_url":"https://syntology.ai/paper/2107.09088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09088"}},"official":{"repos":["dylanashley/reward-weighted-regression"],"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/pc-mlp-model-based-reinforcement-learning","slug":"pc-mlp-model-based-reinforcement-learning","title":"PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration","date":"2021-07-15","arxiv_id":"2107.07410","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":1,"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/pc-mlp-model-based-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2107.07410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07410"}},"official":{"repos":["yudasong/PCMLP"],"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/teaching-agents-how-to-map-spatial-reasoning","slug":"teaching-agents-how-to-map-spatial-reasoning","title":"Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation","date":"2021-07-13","arxiv_id":"2107.06011","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 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) · 1 unverified","sample_list":"/paper/teaching-agents-how-to-map-spatial-reasoning#ran","syntology_url":"https://syntology.ai/paper/2107.06011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06011"}},"official":{"repos":["PierreMarza/teaching_agents_how_to_map"],"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/shortest-path-constrained-reinforcement-1","slug":"shortest-path-constrained-reinforcement-1","title":"Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks","date":"2021-07-13","arxiv_id":"2107.06405","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":0,"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/shortest-path-constrained-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2107.06405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06405"}},"official":{"repos":["srsohn/shortest-path-rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/modeling-explicit-concerning-states-for","slug":"modeling-explicit-concerning-states-for","title":"Modeling Explicit Concerning States for Reinforcement Learning in Visual Dialogue","date":"2021-07-12","arxiv_id":"2107.05250","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/modeling-explicit-concerning-states-for#ran","syntology_url":"https://syntology.ai/paper/2107.05250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05250"}},"official":{"repos":["zipengxuc/ecs-visdial-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/coberl-contrastive-bert-for-reinforcement","slug":"coberl-contrastive-bert-for-reinforcement","title":"CoBERL: Contrastive BERT for Reinforcement Learning","date":"2021-07-12","arxiv_id":"2107.05431","repositories_listed":2,"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/coberl-contrastive-bert-for-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2107.05431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05431"}},"official":{"repos":["deepmind/dm_control"],"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/conservative-offline-distributional","slug":"conservative-offline-distributional","title":"Conservative Offline Distributional Reinforcement Learning","date":"2021-07-12","arxiv_id":"2107.06106","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"4 ran (of which 2 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/conservative-offline-distributional#ran","syntology_url":"https://syntology.ai/paper/2107.06106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06106"}},"official":{"repos":["JasonMa2016/CODAC"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/explore-and-control-with-adversarial-surprise","slug":"explore-and-control-with-adversarial-surprise","title":"Explore and Control with Adversarial Surprise","date":"2021-07-12","arxiv_id":"2107.07394","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/explore-and-control-with-adversarial-surprise#ran","syntology_url":"https://syntology.ai/paper/2107.07394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07394"}},"official":null}},{"url":"/paper/out-of-distribution-dynamics-detection-rl","slug":"out-of-distribution-dynamics-detection-rl","title":"Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and Results","date":"2021-07-11","arxiv_id":"2107.04982","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/out-of-distribution-dynamics-detection-rl#ran","syntology_url":"https://syntology.ai/paper/2107.04982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.04982"}},"official":{"repos":["modanesh/anomalous_rl_envs","modanesh/recurrent_implicit_quantile_networks"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/backprop-free-reinforcement-learning-with","slug":"backprop-free-reinforcement-learning-with","title":"Backprop-Free Reinforcement Learning with Active Neural Generative Coding","date":"2021-07-10","arxiv_id":"2107.07046","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/backprop-free-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2107.07046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07046"}},"official":{"repos":["ago109/active-neural-generative-coding"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/computational-benefits-of-intermediate","slug":"computational-benefits-of-intermediate","title":"Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning","date":"2021-07-08","arxiv_id":"2107.03961","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":1,"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/computational-benefits-of-intermediate#ran","syntology_url":"https://syntology.ai/paper/2107.03961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.03961"}},"official":{"repos":["kebaek/minigrid"],"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/adarl-what-where-and-how-to-adapt-in-transfer","slug":"adarl-what-where-and-how-to-adapt-in-transfer","title":"AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning","date":"2021-07-06","arxiv_id":"2107.02729","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/adarl-what-where-and-how-to-adapt-in-transfer#ran","syntology_url":"https://syntology.ai/paper/2107.02729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02729"}},"official":{"repos":["adaptive-rl/adarl-code"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/ensemble-and-auxiliary-tasks-for-data","slug":"ensemble-and-auxiliary-tasks-for-data","title":"Ensemble and Auxiliary Tasks for Data-Efficient Deep Reinforcement Learning","date":"2021-07-05","arxiv_id":"2107.01904","repositories_listed":1,"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/ensemble-and-auxiliary-tasks-for-data#ran","syntology_url":"https://syntology.ai/paper/2107.01904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.01904"}},"official":{"repos":["NUS-LID/RENAULT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/systematic-evaluation-of-causal-discovery-in-1","slug":"systematic-evaluation-of-causal-discovery-in-1","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","date":"2021-07-02","arxiv_id":"2107.00848","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/systematic-evaluation-of-causal-discovery-in-1#ran","syntology_url":"https://syntology.ai/paper/2107.00848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00848"}},"official":{"repos":["dido1998/CausalMBRL"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/stabilizing-deep-q-learning-with-convnets-and","slug":"stabilizing-deep-q-learning-with-convnets-and","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","date":"2021-07-01","arxiv_id":"2107.00644","repositories_listed":3,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":15,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":14,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/stabilizing-deep-q-learning-with-convnets-and#ran","syntology_url":"https://syntology.ai/paper/2107.00644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00644"}},"official":{"repos":["nicklashansen/dmcontrol-generalization-benchmark"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/habitat-2-0-training-home-assistants-to","slug":"habitat-2-0-training-home-assistants-to","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","date":"2021-06-28","arxiv_id":"2106.14405","repositories_listed":6,"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":2,"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/habitat-2-0-training-home-assistants-to#ran","syntology_url":"https://syntology.ai/paper/2106.14405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14405"}},"official":{"repos":["facebookresearch/habitat-lab"],"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/multi-task-curriculum-learning-in-a-complex","slug":"multi-task-curriculum-learning-in-a-complex","title":"Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft","date":"2021-06-28","arxiv_id":"2106.14876","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/multi-task-curriculum-learning-in-a-complex#ran","syntology_url":"https://syntology.ai/paper/2106.14876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14876"}},"official":null}},{"url":"/paper/multi-goal-reinforcement-learning","slug":"multi-goal-reinforcement-learning","title":"Multi-Goal Reinforcement Learning environments for simulated Franka Emika Panda robot","date":"2021-06-25","arxiv_id":"2106.13687","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/multi-goal-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2106.13687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13687"}},"official":{"repos":["qgallouedec/panda-gym"],"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/compositional-reinforcement-learning-from","slug":"compositional-reinforcement-learning-from","title":"Compositional Reinforcement Learning from Logical Specifications","date":"2021-06-25","arxiv_id":"2106.13906","repositories_listed":1,"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/compositional-reinforcement-learning-from#ran","syntology_url":"https://syntology.ai/paper/2106.13906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13906"}},"official":{"repos":["keyshor/dirl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unifying-gradient-estimators-for-meta","slug":"unifying-gradient-estimators-for-meta","title":"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation","date":"2021-06-24","arxiv_id":"2106.13125","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unifying-gradient-estimators-for-meta#ran","syntology_url":"https://syntology.ai/paper/2106.13125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13125"}},"official":{"repos":["robintyh1/neurips2021-meta-gradient-offpolicy-evaluation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/brax-a-differentiable-physics-engine-for","slug":"brax-a-differentiable-physics-engine-for","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","date":"2021-06-24","arxiv_id":"2106.13281","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/brax-a-differentiable-physics-engine-for#ran","syntology_url":"https://syntology.ai/paper/2106.13281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13281"}},"official":{"repos":["google/brax"],"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/bregman-gradient-policy-optimization","slug":"bregman-gradient-policy-optimization","title":"Bregman Gradient Policy Optimization","date":"2021-06-23","arxiv_id":"2106.12112","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bregman-gradient-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/2106.12112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12112"}},"official":{"repos":["gaosh/bgpo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/local-policy-search-with-bayesian","slug":"local-policy-search-with-bayesian","title":"Local policy search with Bayesian optimization","date":"2021-06-22","arxiv_id":"2106.11899","repositories_listed":3,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/local-policy-search-with-bayesian#ran","syntology_url":"https://syntology.ai/paper/2106.11899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11899"}},"official":{"repos":["sarmueller/gibo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/crop-certifying-robust-policies-for","slug":"crop-certifying-robust-policies-for","title":"CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing","date":"2021-06-17","arxiv_id":"2106.09292","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/crop-certifying-robust-policies-for#ran","syntology_url":"https://syntology.ai/paper/2106.09292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09292"}},"official":{"repos":["ai-secure/crop"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/secant-self-expert-cloning-for-zero-shot","slug":"secant-self-expert-cloning-for-zero-shot","title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies","date":"2021-06-17","arxiv_id":"2106.09678","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/secant-self-expert-cloning-for-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2106.09678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09678"}},"official":{"repos":["LinxiFan/SECANT"],"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/real-time-attacks-against-deep-reinforcement","slug":"real-time-attacks-against-deep-reinforcement","title":"Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses","date":"2021-06-16","arxiv_id":"2106.08746","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/real-time-attacks-against-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2106.08746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08746"}},"official":{"repos":["ssg-research/ad3-action-distribution-divergence-detector"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-the-weaknesses-of-reinforcement-1","slug":"revisiting-the-weaknesses-of-reinforcement-1","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","date":"2021-06-16","arxiv_id":"2106.08942","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/revisiting-the-weaknesses-of-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2106.08942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08942"}},"official":{"repos":["samuki/reinforce-joey"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-reinforcement-learning-using-advantage","slug":"safe-reinforcement-learning-using-advantage","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","date":"2021-06-16","arxiv_id":"2106.09110","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":6,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-reinforcement-learning-using-advantage#ran","syntology_url":"https://syntology.ai/paper/2106.09110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09110"}},"official":{"repos":["nolanwagener/safe_rl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastive-reinforcement-learning-of","slug":"contrastive-reinforcement-learning-of","title":"Contrastive Reinforcement Learning of Symbolic Reasoning Domains","date":"2021-06-16","arxiv_id":"2106.09146","repositories_listed":2,"syntology":{"n":15,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":15,"phrase":"4 ran (of which 1 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) · 11 unverified","sample_list":"/paper/contrastive-reinforcement-learning-of#ran","syntology_url":"https://syntology.ai/paper/2106.09146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09146"}},"official":{"repos":["gpoesia/socratic-tutor"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":11,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/randomized-exploration-for-reinforcement","slug":"randomized-exploration-for-reinforcement","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","date":"2021-06-15","arxiv_id":"2106.07841","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/randomized-exploration-for-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2106.07841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07841"}},"official":{"repos":["qlan3/Explorer"],"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/end-to-end-learning-of-keypoint","slug":"end-to-end-learning-of-keypoint","title":"Learning of feature points without additional supervision improves reinforcement learning from images","date":"2021-06-15","arxiv_id":"2106.07995","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/end-to-end-learning-of-keypoint#ran","syntology_url":"https://syntology.ai/paper/2106.07995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07995"}},"official":{"repos":["rinuboney/fpac","rinuboney/keyq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-reinforcement-learning-under-minimax","slug":"robust-reinforcement-learning-under-minimax","title":"Robust Reinforcement Learning Under Minimax Regret for Green Security","date":"2021-06-15","arxiv_id":"2106.08413","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/robust-reinforcement-learning-under-minimax#ran","syntology_url":"https://syntology.ai/paper/2106.08413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08413"}},"official":{"repos":["lily-x/mirror"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/text-generation-with-efficient-soft-q","slug":"text-generation-with-efficient-soft-q","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","date":"2021-06-14","arxiv_id":"2106.07704","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/text-generation-with-efficient-soft-q#ran","syntology_url":"https://syntology.ai/paper/2106.07704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07704"}},"official":{"repos":["HanGuo97/soft-Q-learning-for-text-generation"],"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/recomposing-the-reinforcement-learning","slug":"recomposing-the-reinforcement-learning","title":"Recomposing the Reinforcement Learning Building Blocks with Hypernetworks","date":"2021-06-12","arxiv_id":"2106.06842","repositories_listed":2,"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/recomposing-the-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2106.06842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06842"}},"official":{"repos":["keynans/HypeRL"],"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/a-deep-reinforcement-learning-approach-to-4","slug":"a-deep-reinforcement-learning-approach-to-4","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","date":"2021-06-12","arxiv_id":"2106.06854","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":4,"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 4 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; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/a-deep-reinforcement-learning-approach-to-4#ran","syntology_url":"https://syntology.ai/paper/2106.06854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06854"}},"official":{"repos":["sfujim/SR-DICE"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-minimalist-approach-to-offline","slug":"a-minimalist-approach-to-offline","title":"A Minimalist Approach to Offline Reinforcement Learning","date":"2021-06-12","arxiv_id":"2106.06860","repositories_listed":8,"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/a-minimalist-approach-to-offline#ran","syntology_url":"https://syntology.ai/paper/2106.06860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06860"}},"official":{"repos":["sfujim/TD3_BC"],"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/douzero-mastering-doudizhu-with-self-play","slug":"douzero-mastering-doudizhu-with-self-play","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","date":"2021-06-11","arxiv_id":"2106.06135","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 1 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) · 3 unverified","sample_list":"/paper/douzero-mastering-doudizhu-with-self-play#ran","syntology_url":"https://syntology.ai/paper/2106.06135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06135"}},"official":{"repos":["kwai/DouZero"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/simplifying-deep-reinforcement-learning-via","slug":"simplifying-deep-reinforcement-learning-via","title":"Simplifying Deep Reinforcement Learning via Self-Supervision","date":"2021-06-10","arxiv_id":"2106.05526","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/simplifying-deep-reinforcement-learning-via#ran","syntology_url":"https://syntology.ai/paper/2106.05526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05526"}},"official":{"repos":["daochenzha/SSRL"],"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/pretraining-representations-for-data","slug":"pretraining-representations-for-data","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","date":"2021-06-09","arxiv_id":"2106.04799","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pretraining-representations-for-data#ran","syntology_url":"https://syntology.ai/paper/2106.04799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04799"}},"official":{"repos":["mila-iqia/SGI"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/who-is-the-strongest-enemy-towards-optimal","slug":"who-is-the-strongest-enemy-towards-optimal","title":"Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL","date":"2021-06-09","arxiv_id":"2106.05087","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":1,"n_instrument":8,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":13,"phrase":"9 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; 8 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/who-is-the-strongest-enemy-towards-optimal#ran","syntology_url":"https://syntology.ai/paper/2106.05087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05087"}},"official":{"repos":["umd-huang-lab/paad_adv_rl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/pebble-feedback-efficient-interactive","slug":"pebble-feedback-efficient-interactive","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","date":"2021-06-09","arxiv_id":"2106.05091","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":1,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"7 ran (of which 1 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) · 0 unverified","sample_list":"/paper/pebble-feedback-efficient-interactive#ran","syntology_url":"https://syntology.ai/paper/2106.05091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05091"}},"official":{"repos":["rll-research/bpref"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/playvirtual-augmenting-cycle-consistent","slug":"playvirtual-augmenting-cycle-consistent","title":"PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning","date":"2021-06-08","arxiv_id":"2106.04152","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":4,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/playvirtual-augmenting-cycle-consistent#ran","syntology_url":"https://syntology.ai/paper/2106.04152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04152"}},"official":{"repos":["microsoft/Playvirtual"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-sparse-training-for-deep","slug":"dynamic-sparse-training-for-deep","title":"Dynamic Sparse Training for Deep Reinforcement Learning","date":"2021-06-08","arxiv_id":"2106.04217","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dynamic-sparse-training-for-deep#ran","syntology_url":"https://syntology.ai/paper/2106.04217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04217"}},"official":{"repos":["GhadaSokar/Dynamic-Sparse-Training-for-Deep-Reinforcement-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/learning-markov-state-abstractions-for-deep","slug":"learning-markov-state-abstractions-for-deep","title":"Learning Markov State Abstractions for Deep Reinforcement Learning","date":"2021-06-08","arxiv_id":"2106.04379","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-markov-state-abstractions-for-deep#ran","syntology_url":"https://syntology.ai/paper/2106.04379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04379"}},"official":{"repos":["camall3n/markov-state-abstractions"],"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/curriculum-design-for-teaching-via","slug":"curriculum-design-for-teaching-via","title":"Curriculum Design for Teaching via Demonstrations: Theory and Applications","date":"2021-06-08","arxiv_id":"2106.04696","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":1,"n_ran_checked":2,"n_instrument":6,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"8 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; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curriculum-design-for-teaching-via#ran","syntology_url":"https://syntology.ai/paper/2106.04696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04696"}},"official":{"repos":["adishs/neurips2021_curriculum-teaching-demonstrations_code"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/task-driven-semantic-coding-via-reinforcement","slug":"task-driven-semantic-coding-via-reinforcement","title":"Task-driven Semantic Coding via Reinforcement Learning","date":"2021-06-07","arxiv_id":"2106.03511","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/task-driven-semantic-coding-via-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2106.03511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03511"}},"official":{"repos":["USTC-IMCL/Task-driven-Semantic-Coding-via-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/correcting-momentum-in-temporal-difference-1","slug":"correcting-momentum-in-temporal-difference-1","title":"Correcting Momentum in Temporal Difference Learning","date":"2021-06-07","arxiv_id":"2106.03955","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/correcting-momentum-in-temporal-difference-1#ran","syntology_url":"https://syntology.ai/paper/2106.03955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03955"}},"official":{"repos":["bengioe/staleness-corrected-momentum"],"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/verifiable-and-compositional-reinforcement","slug":"verifiable-and-compositional-reinforcement","title":"Verifiable and Compositional Reinforcement Learning Systems","date":"2021-06-07","arxiv_id":"2106.05864","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/verifiable-and-compositional-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2106.05864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05864"}},"official":{"repos":["cyrusneary/verifiable-compositional-rl"],"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/control-oriented-model-based-reinforcement","slug":"control-oriented-model-based-reinforcement","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","date":"2021-06-06","arxiv_id":"2106.03273","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/control-oriented-model-based-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2106.03273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03273"}},"official":{"repos":["evgenii-nikishin/omd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/same-state-different-task-continual","slug":"same-state-different-task-continual","title":"Same State, Different Task: Continual Reinforcement Learning without Interference","date":"2021-06-05","arxiv_id":"2106.02940","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/same-state-different-task-continual#ran","syntology_url":"https://syntology.ai/paper/2106.02940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02940"}},"official":{"repos":["skezle/owl"],"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/malib-a-parallel-framework-for-population","slug":"malib-a-parallel-framework-for-population","title":"MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning","date":"2021-06-05","arxiv_id":"2106.07551","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/malib-a-parallel-framework-for-population#ran","syntology_url":"https://syntology.ai/paper/2106.07551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07551"}},"official":{"repos":["sjtu-marl/malib"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-trajectory-representation-learning-for","slug":"cross-trajectory-representation-learning-for","title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL","date":"2021-06-04","arxiv_id":"2106.02193","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":2,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":11,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/cross-trajectory-representation-learning-for#ran","syntology_url":"https://syntology.ai/paper/2106.02193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02193"}},"official":{"repos":["bmazoure/ctrl_public"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/optimization-based-algebraic-multigrid","slug":"optimization-based-algebraic-multigrid","title":"Optimization-Based Algebraic Multigrid Coarsening Using Reinforcement Learning","date":"2021-06-03","arxiv_id":"2106.01854","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/optimization-based-algebraic-multigrid#ran","syntology_url":"https://syntology.ai/paper/2106.01854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01854"}},"official":{"repos":["compdyn/rl_grid_coarsen"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-as-one-big-sequence","slug":"reinforcement-learning-as-one-big-sequence","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","date":"2021-06-03","arxiv_id":"2106.02039","repositories_listed":2,"syntology":{"n":28,"n_ran":23,"n_constructed":0,"n_ran_checked":22,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":21,"n_pointer_only":1,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/reinforcement-learning-as-one-big-sequence#ran","syntology_url":"https://syntology.ai/paper/2106.02039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02039"}},"official":{"repos":["JannerM/trajectory-transformer"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/a-consciousness-inspired-planning-agent-for","slug":"a-consciousness-inspired-planning-agent-for","title":"A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning","date":"2021-06-03","arxiv_id":"2106.02097","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/a-consciousness-inspired-planning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2106.02097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02097"}},"official":{"repos":["mila-iqia/conscious-planning"],"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/mico-learning-improved-representations-via","slug":"mico-learning-improved-representations-via","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","date":"2021-06-03","arxiv_id":"2106.08229","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mico-learning-improved-representations-via#ran","syntology_url":"https://syntology.ai/paper/2106.08229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08229"}},"official":{"repos":["google-research/google-research"],"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/decision-transformer-reinforcement-learning","slug":"decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","arxiv_id":"2106.01345","repositories_listed":20,"syntology":{"n":26,"n_ran":17,"n_constructed":10,"n_ran_checked":13,"n_instrument":4,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":8,"phrase":"17 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/decision-transformer-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2106.01345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01345"}},"official":{"repos":["kzl/decision-transformer"],"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/improving-generalization-in-meta-rl-with","slug":"improving-generalization-in-meta-rl-with","title":"Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture","date":"2021-05-28","arxiv_id":"2105.13524","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/improving-generalization-in-meta-rl-with#ran","syntology_url":"https://syntology.ai/paper/2105.13524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13524"}},"official":{"repos":["suyoung-lee/ldm"],"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/towards-mental-time-travel-a-hierarchical","slug":"towards-mental-time-travel-a-hierarchical","title":"Towards mental time travel: a hierarchical memory for reinforcement learning agents","date":"2021-05-28","arxiv_id":"2105.14039","repositories_listed":5,"syntology":{"n":6,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/towards-mental-time-travel-a-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2105.14039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14039"}},"official":{"repos":["deepmind/deepmind-research","deepmind/dm_fast_mapping"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/objective-robustness-in-deep-reinforcement","slug":"objective-robustness-in-deep-reinforcement","title":"Goal Misgeneralization in Deep Reinforcement Learning","date":"2021-05-28","arxiv_id":"2105.14111","repositories_listed":4,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/objective-robustness-in-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2105.14111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14111"}},"official":{"repos":["JacobPfau/procgenAISC","jbkjr/train-procgen-pytorch"],"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":["listed","official"]}}},{"url":"/paper/androidenv-a-reinforcement-learning-platform","slug":"androidenv-a-reinforcement-learning-platform","title":"AndroidEnv: A Reinforcement Learning Platform for Android","date":"2021-05-27","arxiv_id":"2105.13231","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/androidenv-a-reinforcement-learning-platform#ran","syntology_url":"https://syntology.ai/paper/2105.13231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13231"}},"official":{"repos":["deepmind/android_env"],"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/adversarial-intrinsic-motivation-for","slug":"adversarial-intrinsic-motivation-for","title":"Adversarial Intrinsic Motivation for Reinforcement Learning","date":"2021-05-27","arxiv_id":"2105.13345","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"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) · 4 unverified","sample_list":"/paper/adversarial-intrinsic-motivation-for#ran","syntology_url":"https://syntology.ai/paper/2105.13345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13345"}},"official":{"repos":["iDurugkar/adversarial-intrinsic-motivation"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/feasible-actor-critic-constrained","slug":"feasible-actor-critic-constrained","title":"Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety","date":"2021-05-22","arxiv_id":"2105.10682","repositories_listed":3,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/feasible-actor-critic-constrained#ran","syntology_url":"https://syntology.ai/paper/2105.10682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.10682"}},"official":{"repos":["mahaitongdae/Feasible-Actor-Critic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/on-instrumental-variable-regression-for-deep","slug":"on-instrumental-variable-regression-for-deep","title":"On Instrumental Variable Regression for Deep Offline Policy Evaluation","date":"2021-05-21","arxiv_id":"2105.10148","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/on-instrumental-variable-regression-for-deep#ran","syntology_url":"https://syntology.ai/paper/2105.10148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.10148"}},"official":{"repos":["liyuan9988/IVOPEwithACME"],"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/minimum-delay-adaptation-in-non-stationary","slug":"minimum-delay-adaptation-in-non-stationary","title":"Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection","date":"2021-05-20","arxiv_id":"2105.09452","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"10 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/minimum-delay-adaptation-in-non-stationary#ran","syntology_url":"https://syntology.ai/paper/2105.09452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.09452"}},"official":{"repos":["LucasAlegre/mbcd"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/coach-player-multi-agent-reinforcement","slug":"coach-player-multi-agent-reinforcement","title":"Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition","date":"2021-05-18","arxiv_id":"2105.08692","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/coach-player-multi-agent-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2105.08692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08692"}},"official":{"repos":["cranial-xix/marl-copa"],"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/principled-exploration-via-optimistic","slug":"principled-exploration-via-optimistic","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","date":"2021-05-13","arxiv_id":"2105.06022","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":12,"phrase":"6 ran (of which 0 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) · 6 unverified","sample_list":"/paper/principled-exploration-via-optimistic#ran","syntology_url":"https://syntology.ai/paper/2105.06022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.06022"}},"official":{"repos":["Baichenjia/OB2I"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/meta-learning-based-deep-reinforcement","slug":"meta-learning-based-deep-reinforcement","title":"Meta-Learning-Based Deep Reinforcement Learning for Multiobjective Optimization Problems","date":"2021-05-06","arxiv_id":"2105.02741","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/meta-learning-based-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2105.02741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.02741"}},"official":{"repos":["zhangzizhen/ml-dam"],"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/adapting-to-reward-progressivity-via-spectral-1","slug":"adapting-to-reward-progressivity-via-spectral-1","title":"Adapting to Reward Progressivity via Spectral Reinforcement Learning","date":"2021-04-29","arxiv_id":"2104.14138","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/adapting-to-reward-progressivity-via-spectral-1#ran","syntology_url":"https://syntology.ai/paper/2104.14138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14138"}},"official":{"repos":["mchldann/SpectralDQN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-navigation-with-spatial-attention","slug":"visual-navigation-with-spatial-attention","title":"Visual Navigation with Spatial Attention","date":"2021-04-20","arxiv_id":"2104.09807","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/visual-navigation-with-spatial-attention#ran","syntology_url":"https://syntology.ai/paper/2104.09807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09807"}},"official":null}},{"url":"/paper/probabilistic-mixture-of-experts-for-1","slug":"probabilistic-mixture-of-experts-for-1","title":"Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning","date":"2021-04-19","arxiv_id":"2104.09122","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/probabilistic-mixture-of-experts-for-1#ran","syntology_url":"https://syntology.ai/paper/2104.09122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09122"}},"official":{"repos":["JieRen98/rlkit-pmoe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generalising-discrete-action-spaces-with","slug":"generalising-discrete-action-spaces-with","title":"Generalising Discrete Action Spaces with Conditional Action Trees","date":"2021-04-15","arxiv_id":"2104.07294","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/generalising-discrete-action-spaces-with#ran","syntology_url":"https://syntology.ai/paper/2104.07294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07294"}},"official":{"repos":["Bam4d/conditional-action-trees"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-continuous-control-with-constrained","slug":"safe-continuous-control-with-constrained","title":"Safe Continuous Control with Constrained Model-Based Policy Optimization","date":"2021-04-14","arxiv_id":"2104.06922","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":1,"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-continuous-control-with-constrained#ran","syntology_url":"https://syntology.ai/paper/2104.06922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06922"}},"official":null}},{"url":"/paper/podracer-architectures-for-scalable","slug":"podracer-architectures-for-scalable","title":"Podracer architectures for scalable Reinforcement Learning","date":"2021-04-13","arxiv_id":"2104.06272","repositories_listed":3,"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/podracer-architectures-for-scalable#ran","syntology_url":"https://syntology.ai/paper/2104.06272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06272"}},"official":null}},{"url":"/paper/character-controllers-using-motion-vaes","slug":"character-controllers-using-motion-vaes","title":"Character Controllers Using Motion VAEs","date":"2021-03-26","arxiv_id":"2103.14274","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/character-controllers-using-motion-vaes#ran","syntology_url":"https://syntology.ai/paper/2103.14274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14274"}},"official":{"repos":["electronicarts/character-motion-vaes"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/model-predictive-actor-critic-accelerating","slug":"model-predictive-actor-critic-accelerating","title":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","date":"2021-03-25","arxiv_id":"2103.13842","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/model-predictive-actor-critic-accelerating#ran","syntology_url":"https://syntology.ai/paper/2103.13842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13842"}},"official":{"repos":["dnandha/mopac"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/solving-compositional-reinforcement-learning-1","slug":"solving-compositional-reinforcement-learning-1","title":"Solving Compositional Reinforcement Learning Problems via Task Reduction","date":"2021-03-13","arxiv_id":"2103.07607","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/solving-compositional-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2103.07607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07607"}},"official":{"repos":["IrisLi17/self-imitation-via-reduction"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/xdo-a-double-oracle-algorithm-for-extensive","slug":"xdo-a-double-oracle-algorithm-for-extensive","title":"XDO: A Double Oracle Algorithm for Extensive-Form Games","date":"2021-03-11","arxiv_id":"2103.06426","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"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) · 4 unverified","sample_list":"/paper/xdo-a-double-oracle-algorithm-for-extensive#ran","syntology_url":"https://syntology.ai/paper/2103.06426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06426"}},"official":{"repos":["indylab/nxdo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["community","official"]}}},{"url":"/paper/generalizable-episodic-memory-for-deep","slug":"generalizable-episodic-memory-for-deep","title":"Generalizable Episodic Memory for Deep Reinforcement Learning","date":"2021-03-11","arxiv_id":"2103.06469","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":1,"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/generalizable-episodic-memory-for-deep#ran","syntology_url":"https://syntology.ai/paper/2103.06469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06469"}},"official":{"repos":["MouseHu/GEM"],"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/behavior-from-the-void-unsupervised-active","slug":"behavior-from-the-void-unsupervised-active","title":"Behavior From the Void: Unsupervised Active Pre-Training","date":"2021-03-08","arxiv_id":"2103.04551","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/behavior-from-the-void-unsupervised-active#ran","syntology_url":"https://syntology.ai/paper/2103.04551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.04551"}},"official":{"repos":["rll-research/url_benchmark"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/model-based-safe-reinforcement-learning-using","slug":"model-based-safe-reinforcement-learning-using","title":"Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function","date":"2021-03-02","arxiv_id":"2103.01556","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/model-based-safe-reinforcement-learning-using#ran","syntology_url":"https://syntology.ai/paper/2103.01556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01556"}},"official":{"repos":["mahaitongdae/safe_exp_env"],"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/the-surprising-effectiveness-of-mappo-in","slug":"the-surprising-effectiveness-of-mappo-in","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","date":"2021-03-02","arxiv_id":"2103.01955","repositories_listed":19,"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/the-surprising-effectiveness-of-mappo-in#ran","syntology_url":"https://syntology.ai/paper/2103.01955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01955"}},"official":{"repos":["marlbenchmark/on-policy"],"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/hierarchical-and-partially-observable-goal","slug":"hierarchical-and-partially-observable-goal","title":"Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph","date":"2021-03-01","arxiv_id":"2103.01350","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":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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/hierarchical-and-partially-observable-goal#ran","syntology_url":"https://syntology.ai/paper/2103.01350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01350"}},"official":{"repos":["Xin-Ye-1/HRL-GRG"],"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/robust-deep-reinforcement-learning-via-multi","slug":"robust-deep-reinforcement-learning-via-multi","title":"DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck","date":"2021-02-26","arxiv_id":"2102.13268","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 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; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-deep-reinforcement-learning-via-multi#ran","syntology_url":"https://syntology.ai/paper/2102.13268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.13268"}},"official":{"repos":["BU-DEPEND-Lab/DRIBO"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-probabilistic-interpretation-of-self-paced","slug":"a-probabilistic-interpretation-of-self-paced","title":"A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning","date":"2021-02-25","arxiv_id":"2102.13176","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-probabilistic-interpretation-of-self-paced#ran","syntology_url":"https://syntology.ai/paper/2102.13176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.13176"}},"official":{"repos":["psclklnk/self-paced-rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/memory-based-deep-reinforcement-learning-for-1","slug":"memory-based-deep-reinforcement-learning-for-1","title":"Memory-based Deep Reinforcement Learning for POMDPs","date":"2021-02-24","arxiv_id":"2102.12344","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/memory-based-deep-reinforcement-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2102.12344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12344"}},"official":{"repos":["LinghengMeng/LSTM-TD3"],"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/information-directed-reward-learning-for","slug":"information-directed-reward-learning-for","title":"Information Directed Reward Learning for Reinforcement Learning","date":"2021-02-24","arxiv_id":"2102.12466","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/information-directed-reward-learning-for#ran","syntology_url":"https://syntology.ai/paper/2102.12466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12466"}},"official":{"repos":["david-lindner/idrl"],"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/mixed-policy-gradient","slug":"mixed-policy-gradient","title":"Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and model","date":"2021-02-23","arxiv_id":"2102.11513","repositories_listed":2,"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/mixed-policy-gradient#ran","syntology_url":"https://syntology.ai/paper/2102.11513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11513"}},"official":null}},{"url":"/paper/program-synthesis-guided-reinforcement","slug":"program-synthesis-guided-reinforcement","title":"Program Synthesis Guided Reinforcement Learning for Partially Observed Environments","date":"2021-02-22","arxiv_id":"2102.11137","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/program-synthesis-guided-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2102.11137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11137"}},"official":{"repos":["yycdavid/program-synthesis-guided-rl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/explore-the-context-optimal-data-collection","slug":"explore-the-context-optimal-data-collection","title":"Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models","date":"2021-02-22","arxiv_id":"2102.11394","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/explore-the-context-optimal-data-collection#ran","syntology_url":"https://syntology.ai/paper/2102.11394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11394"}},"official":null}},{"url":"/paper/continuous-doubly-constrained-batch","slug":"continuous-doubly-constrained-batch","title":"Continuous Doubly Constrained Batch Reinforcement Learning","date":"2021-02-18","arxiv_id":"2102.09225","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":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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/continuous-doubly-constrained-batch#ran","syntology_url":"https://syntology.ai/paper/2102.09225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.09225"}},"official":{"repos":["amazon-research/cdc-batch-rl"],"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"]}}}],"record_sha256":"5d44812b61ac26787292f782599db0da2c45b4a55059decfc50d3bdf82515458","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}