{"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/q-learning/papers/ran/1","list_of":"/task/q-learning","task":"Q-Learning","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":1,"pages_in_order":2,"rows_per_page":100,"rows":[1,100],"of":119,"counts":{"archive_papers_tagged":1918,"with_a_code_link":463,"where_syntology_ran_a_sample":119,"not_listed_spam_title":0,"listed":1918,"listed_where_code_ran":119,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":102,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":102,"listed_every_run_a_failure_of_syntologys_instrument":17,"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/q-learning/papers/ran/1","prev":null,"next":"/task/q-learning/papers/ran/2","papers":[{"url":"/paper/meta-black-box-optimization-through-offline-q","slug":"meta-black-box-optimization-through-offline-q","title":"Meta-Black-Box-Optimization through Offline Q-function Learning","date":"2025-05-04","arxiv_id":"2505.02010","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"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) · 3 unverified","sample_list":"/paper/meta-black-box-optimization-through-offline-q#ran","syntology_url":"https://syntology.ai/paper/2505.02010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02010"}},"official":{"repos":["metaevo/q-mamba"],"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","unlocated"]}}},{"url":"/paper/popgym-arcade-parallel-pixelated-pomdps","slug":"popgym-arcade-parallel-pixelated-pomdps","title":"POPGym Arcade: Parallel Pixelated POMDPs","date":"2025-03-03","arxiv_id":"2503.01450","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/popgym-arcade-parallel-pixelated-pomdps#ran","syntology_url":"https://syntology.ai/paper/2503.01450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01450"}},"official":{"repos":["bolt-research/popgym_arcade"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/digi-q-learning-q-value-functions-for","slug":"digi-q-learning-q-value-functions-for","title":"Digi-Q: Learning Q-Value Functions for Training Device-Control Agents","date":"2025-02-13","arxiv_id":"2502.15760","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/digi-q-learning-q-value-functions-for#ran","syntology_url":"https://syntology.ai/paper/2502.15760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15760"}},"official":{"repos":["digirl-agent/digiq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/conrft-a-reinforced-fine-tuning-method-for","slug":"conrft-a-reinforced-fine-tuning-method-for","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy","date":"2025-02-08","arxiv_id":"2502.05450","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/conrft-a-reinforced-fine-tuning-method-for#ran","syntology_url":"https://syntology.ai/paper/2502.05450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05450"}},"official":{"repos":["cccedric/conrft"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/flow-q-learning","slug":"flow-q-learning","title":"Flow Q-Learning","date":"2025-02-04","arxiv_id":"2502.02538","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/flow-q-learning#ran","syntology_url":"https://syntology.ai/paper/2502.02538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02538"}},"official":{"repos":["seohongpark/fql"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/temporal-difference-learning-using","slug":"temporal-difference-learning-using","title":"Temporal-Difference Learning Using Distributed Error Signals","date":"2024-11-06","arxiv_id":"2411.03604","repositories_listed":1,"syntology":{"n":24,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":14,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/temporal-difference-learning-using#ran","syntology_url":"https://syntology.ai/paper/2411.03604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03604"}},"official":{"repos":["social-ai-uoft/ad-paper"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/q-distribution-guided-q-learning-for-offline","slug":"q-distribution-guided-q-learning-for-offline","title":"Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model","date":"2024-10-27","arxiv_id":"2410.20312","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/q-distribution-guided-q-learning-for-offline#ran","syntology_url":"https://syntology.ai/paper/2410.20312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20312"}},"official":{"repos":["evalarzj/qdq"],"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/streaming-deep-reinforcement-learning-finally","slug":"streaming-deep-reinforcement-learning-finally","title":"Streaming Deep Reinforcement Learning Finally Works","date":"2024-10-18","arxiv_id":"2410.14606","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":3,"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/streaming-deep-reinforcement-learning-finally#ran","syntology_url":"https://syntology.ai/paper/2410.14606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14606"}},"official":{"repos":["mohmdelsayed/streaming-drl"],"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/hard-prompts-made-interpretable-sparse","slug":"hard-prompts-made-interpretable-sparse","title":"Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL","date":"2024-07-20","arxiv_id":"2407.14733","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":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) · 1 unverified","sample_list":"/paper/hard-prompts-made-interpretable-sparse#ran","syntology_url":"https://syntology.ai/paper/2407.14733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14733"}},"official":{"repos":["youseob/pin"],"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/a-two-step-minimax-q-learning-algorithm-for","slug":"a-two-step-minimax-q-learning-algorithm-for","title":"A Multi-Step Minimax Q-learning Algorithm for Two-Player Zero-Sum Markov Games","date":"2024-07-05","arxiv_id":"2407.04240","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-two-step-minimax-q-learning-algorithm-for#ran","syntology_url":"https://syntology.ai/paper/2407.04240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04240"}},"official":{"repos":["shreyassr123/multi-step-markov-games"],"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/simplifying-deep-temporal-difference-learning","slug":"simplifying-deep-temporal-difference-learning","title":"Simplifying Deep Temporal Difference Learning","date":"2024-07-05","arxiv_id":"2407.04811","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":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/simplifying-deep-temporal-difference-learning#ran","syntology_url":"https://syntology.ai/paper/2407.04811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04811"}},"official":{"repos":["mttga/purejaxql"],"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/q-adapter-training-your-llm-adapter-as-a","slug":"q-adapter-training-your-llm-adapter-as-a","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","date":"2024-07-04","arxiv_id":"2407.03856","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"13 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/q-adapter-training-your-llm-adapter-as-a#ran","syntology_url":"https://syntology.ai/paper/2407.03856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03856"}},"official":{"repos":["mansicer/Q-Adapter"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/target-networks-and-over-parameterization","slug":"target-networks-and-over-parameterization","title":"Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation","date":"2024-05-31","arxiv_id":"2405.21043","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/target-networks-and-over-parameterization#ran","syntology_url":"https://syntology.ai/paper/2405.21043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.21043"}},"official":{"repos":["FengdiC/OTTD"],"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/diffusion-policies-creating-a-trust-region","slug":"diffusion-policies-creating-a-trust-region","title":"Diffusion Policies creating a Trust Region for Offline Reinforcement Learning","date":"2024-05-30","arxiv_id":"2405.19690","repositories_listed":1,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":20,"phrase":"17 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; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diffusion-policies-creating-a-trust-region#ran","syntology_url":"https://syntology.ai/paper/2405.19690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19690"}},"official":{"repos":["tianyucodings/diffusion_trusted_q_learning"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-recipe-for-unbounded-data-augmentation-in","slug":"a-recipe-for-unbounded-data-augmentation-in","title":"A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning","date":"2024-05-27","arxiv_id":"2405.17416","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"13 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-recipe-for-unbounded-data-augmentation-in#ran","syntology_url":"https://syntology.ai/paper/2405.17416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17416"}},"official":{"repos":["aalmuzairee/dmcgb2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/scalable-online-exploration-via-coverability","slug":"scalable-online-exploration-via-coverability","title":"Scalable Online Exploration via Coverability","date":"2024-03-11","arxiv_id":"2403.06571","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/scalable-online-exploration-via-coverability#ran","syntology_url":"https://syntology.ai/paper/2403.06571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06571"}},"official":{"repos":["philip-amortila/l1-coverability"],"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/belief-enriched-pessimistic-q-learning","slug":"belief-enriched-pessimistic-q-learning","title":"Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations","date":"2024-03-06","arxiv_id":"2403.04050","repositories_listed":1,"syntology":{"n":24,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":10,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":24,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/belief-enriched-pessimistic-q-learning#ran","syntology_url":"https://syntology.ai/paper/2403.04050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04050"}},"official":{"repos":["sliencerx/belief-enriched-robust-q-learning"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-episodic-memory-utilization-of","slug":"efficient-episodic-memory-utilization-of","title":"Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning","date":"2024-03-02","arxiv_id":"2403.01112","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/efficient-episodic-memory-utilization-of#ran","syntology_url":"https://syntology.ai/paper/2403.01112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01112"}},"official":{"repos":["hyunghona/emu"],"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":["official"]}}},{"url":"/paper/subiq-inverse-soft-q-learning-for-offline","slug":"subiq-inverse-soft-q-learning-for-offline","title":"SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning","date":"2024-02-20","arxiv_id":"2402.13147","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":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) · 1 unverified","sample_list":"/paper/subiq-inverse-soft-q-learning-for-offline#ran","syntology_url":"https://syntology.ai/paper/2402.13147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13147"}},"official":{"repos":["hmhuy0/SPRINQL"],"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/conservative-and-risk-aware-offline-multi","slug":"conservative-and-risk-aware-offline-multi","title":"Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning","date":"2024-02-13","arxiv_id":"2402.08421","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/conservative-and-risk-aware-offline-multi#ran","syntology_url":"https://syntology.ai/paper/2402.08421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08421"}},"official":{"repos":["eslam211/conservative-and-distributional-marl"],"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/towards-optimal-adversarial-robust-q-learning","slug":"towards-optimal-adversarial-robust-q-learning","title":"Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error","date":"2024-02-03","arxiv_id":"2402.02165","repositories_listed":2,"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":8,"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/towards-optimal-adversarial-robust-q-learning#ran","syntology_url":"https://syntology.ai/paper/2402.02165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02165"}},"official":{"repos":["leoranlmia/CAR-DQN"],"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/spqr-controlling-q-ensemble-independence-with-1","slug":"spqr-controlling-q-ensemble-independence-with-1","title":"SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning","date":"2024-01-06","arxiv_id":"2401.03137","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/spqr-controlling-q-ensemble-independence-with-1#ran","syntology_url":"https://syntology.ai/paper/2401.03137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03137"}},"official":{"repos":["dohyeoklee/SPQR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/optimistic-multi-agent-policy-gradient-for","slug":"optimistic-multi-agent-policy-gradient-for","title":"Optimistic Multi-Agent Policy Gradient","date":"2023-11-03","arxiv_id":"2311.01953","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/optimistic-multi-agent-policy-gradient-for#ran","syntology_url":"https://syntology.ai/paper/2311.01953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01953"}},"official":{"repos":["wenshuaizhao/optimappo"],"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/weakly-coupled-deep-q-networks","slug":"weakly-coupled-deep-q-networks","title":"Weakly Coupled Deep Q-Networks","date":"2023-10-28","arxiv_id":"2310.18803","repositories_listed":0,"syntology":{"n":10,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":10,"phrase":"5 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; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/weakly-coupled-deep-q-networks#ran","syntology_url":"https://syntology.ai/paper/2310.18803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18803"}},"official":null}},{"url":"/paper/towards-robust-offline-reinforcement-learning","slug":"towards-robust-offline-reinforcement-learning","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","date":"2023-10-19","arxiv_id":"2310.12955","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"5 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/towards-robust-offline-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2310.12955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12955"}},"official":{"repos":["yangrui2015/riql"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/boosting-continuous-control-with-consistency","slug":"boosting-continuous-control-with-consistency","title":"Boosting Continuous Control with Consistency Policy","date":"2023-10-10","arxiv_id":"2310.06343","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/boosting-continuous-control-with-consistency#ran","syntology_url":"https://syntology.ai/paper/2310.06343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06343"}},"official":{"repos":["cccedric/cpql"],"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/pre-training-with-synthetic-data-helps","slug":"pre-training-with-synthetic-data-helps","title":"Pre-training with Synthetic Data Helps Offline Reinforcement Learning","date":"2023-10-01","arxiv_id":"2310.00771","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/pre-training-with-synthetic-data-helps#ran","syntology_url":"https://syntology.ai/paper/2310.00771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00771"}},"official":{"repos":["victor-wang-902/synthetic-pretrain-rl"],"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/counterfactual-conservative-q-learning-for-1","slug":"counterfactual-conservative-q-learning-for-1","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning","date":"2023-09-22","arxiv_id":"2309.12696","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":3,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"7 ran (of which 3 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/counterfactual-conservative-q-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2309.12696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12696"}},"official":{"repos":["thu-rllab/CFCQL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/reasoning-with-latent-diffusion-in-offline","slug":"reasoning-with-latent-diffusion-in-offline","title":"Reasoning with Latent Diffusion in Offline Reinforcement Learning","date":"2023-09-12","arxiv_id":"2309.06599","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":6,"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/reasoning-with-latent-diffusion-in-offline#ran","syntology_url":"https://syntology.ai/paper/2309.06599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06599"}},"official":{"repos":["ldcq/ldcq"],"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/towards-few-shot-coordination-revisiting-ad","slug":"towards-few-shot-coordination-revisiting-ad","title":"Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi","date":"2023-08-20","arxiv_id":"2308.10284","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/towards-few-shot-coordination-revisiting-ad#ran","syntology_url":"https://syntology.ai/paper/2308.10284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10284"}},"official":{"repos":["chandar-lab/adaptive-hanabi"],"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/robust-multi-agent-reinforcement-learning-3","slug":"robust-multi-agent-reinforcement-learning-3","title":"Robust Multi-Agent Reinforcement Learning with State Uncertainty","date":"2023-07-30","arxiv_id":"2307.16212","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/robust-multi-agent-reinforcement-learning-3#ran","syntology_url":"https://syntology.ai/paper/2307.16212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.16212"}},"official":{"repos":["sihongho/robust_marl_with_state_uncertainty"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/parallel-q-learning-scaling-off-policy","slug":"parallel-q-learning-scaling-off-policy","title":"Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation","date":"2023-07-24","arxiv_id":"2307.12983","repositories_listed":0,"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/parallel-q-learning-scaling-off-policy#ran","syntology_url":"https://syntology.ai/paper/2307.12983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12983"}},"official":null}},{"url":"/paper/madiff-offline-multi-agent-learning-with","slug":"madiff-offline-multi-agent-learning-with","title":"MADiff: Offline Multi-agent Learning with Diffusion Models","date":"2023-05-27","arxiv_id":"2305.17330","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/madiff-offline-multi-agent-learning-with#ran","syntology_url":"https://syntology.ai/paper/2305.17330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17330"}},"official":{"repos":["zbzhu99/madiff"],"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/2305-14550","slug":"2305-14550","title":"When should we prefer Decision Transformers for Offline Reinforcement Learning?","date":"2023-05-23","arxiv_id":"2305.14550","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":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) · 2 unverified","sample_list":"/paper/2305-14550#ran","syntology_url":"https://syntology.ai/paper/2305.14550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14550"}},"official":{"repos":["prajjwal1/rl_paradigm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/idql-implicit-q-learning-as-an-actor-critic","slug":"idql-implicit-q-learning-as-an-actor-critic","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","date":"2023-04-20","arxiv_id":"2304.10573","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/idql-implicit-q-learning-as-an-actor-critic#ran","syntology_url":"https://syntology.ai/paper/2304.10573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10573"}},"official":{"repos":["philippe-eecs/idql"],"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","unlocated"]}}},{"url":"/paper/offline-rl-with-no-ood-actions-in-sample","slug":"offline-rl-with-no-ood-actions-in-sample","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","date":"2023-03-28","arxiv_id":"2303.15810","repositories_listed":4,"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/offline-rl-with-no-ood-actions-in-sample#ran","syntology_url":"https://syntology.ai/paper/2303.15810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15810"}},"official":{"repos":["ryanxhr/ivr"],"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/extreme-q-learning-maxent-rl-without-entropy","slug":"extreme-q-learning-maxent-rl-without-entropy","title":"Extreme Q-Learning: MaxEnt RL without Entropy","date":"2023-01-05","arxiv_id":"2301.02328","repositories_listed":4,"syntology":{"n":13,"n_ran":8,"n_constructed":5,"n_ran_checked":5,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/extreme-q-learning-maxent-rl-without-entropy#ran","syntology_url":"https://syntology.ai/paper/2301.02328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02328"}},"official":null}},{"url":"/paper/a-machine-with-short-term-episodic-and","slug":"a-machine-with-short-term-episodic-and","title":"A Machine with Short-Term, Episodic, and Semantic Memory Systems","date":"2022-12-05","arxiv_id":"2212.02098","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/a-machine-with-short-term-episodic-and#ran","syntology_url":"https://syntology.ai/paper/2212.02098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.02098"}},"official":{"repos":["humemai/agent-room-env-v1"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/welfare-and-fairness-in-multi-objective","slug":"welfare-and-fairness-in-multi-objective","title":"Welfare and Fairness in Multi-objective Reinforcement Learning","date":"2022-11-30","arxiv_id":"2212.01382","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 3 unverified","sample_list":"/paper/welfare-and-fairness-in-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2212.01382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.01382"}},"official":{"repos":["MuhangTian/Fair-MORL-AAMAS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ace-cooperative-multi-agent-q-learning-with","slug":"ace-cooperative-multi-agent-q-learning-with","title":"ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency","date":"2022-11-29","arxiv_id":"2211.16068","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/ace-cooperative-multi-agent-q-learning-with#ran","syntology_url":"https://syntology.ai/paper/2211.16068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.16068"}},"official":{"repos":["opendilab/ace"],"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/solving-continuous-control-via-q-learning","slug":"solving-continuous-control-via-q-learning","title":"Solving Continuous Control via Q-learning","date":"2022-10-22","arxiv_id":"2210.12566","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":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) · 3 unverified","sample_list":"/paper/solving-continuous-control-via-q-learning#ran","syntology_url":"https://syntology.ai/paper/2210.12566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12566"}},"official":{"repos":["tseyde/decqn"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/mutual-information-regularized-offline-1","slug":"mutual-information-regularized-offline-1","title":"Mutual Information Regularized Offline Reinforcement Learning","date":"2022-10-14","arxiv_id":"2210.07484","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mutual-information-regularized-offline-1#ran","syntology_url":"https://syntology.ai/paper/2210.07484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07484"}},"official":{"repos":["sail-sg/misa"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hybrid-rl-using-both-offline-and-online-data","slug":"hybrid-rl-using-both-offline-and-online-data","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","date":"2022-10-13","arxiv_id":"2210.06718","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"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; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hybrid-rl-using-both-offline-and-online-data#ran","syntology_url":"https://syntology.ai/paper/2210.06718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06718"}},"official":{"repos":["yudasong/hyq"],"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/towards-safe-mechanical-ventilation-treatment","slug":"towards-safe-mechanical-ventilation-treatment","title":"Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning","date":"2022-10-05","arxiv_id":"2210.02552","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/towards-safe-mechanical-ventilation-treatment#ran","syntology_url":"https://syntology.ai/paper/2210.02552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02552"}},"official":{"repos":["FlemmingKondrup/DeepVent"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-q-learning-algorithm-for-markov","slug":"robust-q-learning-algorithm-for-markov","title":"Robust $Q$-learning Algorithm for Markov Decision Processes under Wasserstein Uncertainty","date":"2022-09-30","arxiv_id":"2210.00898","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 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) · 1 unverified","sample_list":"/paper/robust-q-learning-algorithm-for-markov#ran","syntology_url":"https://syntology.ai/paper/2210.00898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.00898"}},"official":{"repos":["juliansester/wasserstein-q-learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-policies-as-an-expressive-policy","slug":"diffusion-policies-as-an-expressive-policy","title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","date":"2022-08-12","arxiv_id":"2208.06193","repositories_listed":3,"syntology":{"n":18,"n_ran":11,"n_constructed":5,"n_ran_checked":11,"n_instrument":0,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":10,"phrase":"11 ran (of which 5 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) · 7 unverified","sample_list":"/paper/diffusion-policies-as-an-expressive-policy#ran","syntology_url":"https://syntology.ai/paper/2208.06193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.06193"}},"official":{"repos":["zhendong-wang/diffusion-policies-for-offline-rl"],"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":["listed","official"]}}},{"url":"/paper/a-deep-reinforcement-learning-approach-for-13","slug":"a-deep-reinforcement-learning-approach-for-13","title":"A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games","date":"2022-07-18","arxiv_id":"2207.08894","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"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) · 5 unverified","sample_list":"/paper/a-deep-reinforcement-learning-approach-for-13#ran","syntology_url":"https://syntology.ai/paper/2207.08894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.08894"}},"official":{"repos":["quantumiracle/mars","quantumiracle/nash-dqn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-learning-and-learnablity-of","slug":"on-the-learning-and-learnablity-of","title":"On the Learning and Learnability of Quasimetrics","date":"2022-06-30","arxiv_id":"2206.15478","repositories_listed":2,"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/on-the-learning-and-learnablity-of#ran","syntology_url":"https://syntology.ai/paper/2206.15478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.15478"}},"official":{"repos":["ssnl/poisson_quasimetric_embedding"],"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/mildly-conservative-q-learning-for-offline","slug":"mildly-conservative-q-learning-for-offline","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","date":"2022-06-09","arxiv_id":"2206.04745","repositories_listed":3,"syntology":{"n":16,"n_ran":13,"n_constructed":6,"n_ran_checked":13,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":12,"n_pointer_only":11,"phrase":"13 ran (of which 6 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mildly-conservative-q-learning-for-offline#ran","syntology_url":"https://syntology.ai/paper/2206.04745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04745"}},"official":{"repos":["dmksjfl/mcq"],"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","listed"]}}},{"url":"/paper/offline-rl-for-natural-language-generation","slug":"offline-rl-for-natural-language-generation","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","date":"2022-06-05","arxiv_id":"2206.11871","repositories_listed":2,"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":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/offline-rl-for-natural-language-generation#ran","syntology_url":"https://syntology.ai/paper/2206.11871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.11871"}},"official":null}},{"url":"/paper/cclf-a-contrastive-curiosity-driven-learning","slug":"cclf-a-contrastive-curiosity-driven-learning","title":"CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning","date":"2022-05-02","arxiv_id":"2205.00943","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cclf-a-contrastive-curiosity-driven-learning#ran","syntology_url":"https://syntology.ai/paper/2205.00943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.00943"}},"official":{"repos":["csun001/cclf"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/polyak-ruppert-averaged-q-leaning-is","slug":"polyak-ruppert-averaged-q-leaning-is","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","date":"2021-12-29","arxiv_id":"2112.14582","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/polyak-ruppert-averaged-q-leaning-is#ran","syntology_url":"https://syntology.ai/paper/2112.14582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.14582"}},"official":{"repos":["lx10077/AveQLearning"],"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/offline-reinforcement-learning-with-implicit","slug":"offline-reinforcement-learning-with-implicit","title":"Offline Reinforcement Learning with Implicit Q-Learning","date":"2021-10-12","arxiv_id":"2110.06169","repositories_listed":17,"syntology":{"n":58,"n_ran":45,"n_constructed":23,"n_ran_checked":37,"n_instrument":8,"n_unverified":13,"n_honours":0,"n_violates":0,"n_no_contract":37,"n_pointer_only":23,"phrase":"45 ran (of which 23 constructed an object rather than computing a result; 37 with no instrument failure: 0 honoured, 0 violated, 37 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/offline-reinforcement-learning-with-implicit#ran","syntology_url":"https://syntology.ai/paper/2110.06169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06169"}},"official":{"repos":["rail-berkeley/rlkit","ikostrikov/implicit_q_learning"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/dropout-q-functions-for-doubly-efficient","slug":"dropout-q-functions-for-doubly-efficient","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","date":"2021-10-05","arxiv_id":"2110.02034","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":3,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dropout-q-functions-for-doubly-efficient#ran","syntology_url":"https://syntology.ai/paper/2110.02034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02034"}},"official":{"repos":["TakuyaHiraoka/Dropout-Q-Functions-for-Doubly-Efficient-Reinforcement-Learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/uncertainty-based-offline-reinforcement","slug":"uncertainty-based-offline-reinforcement","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","date":"2021-10-04","arxiv_id":"2110.01548","repositories_listed":5,"syntology":{"n":21,"n_ran":13,"n_constructed":11,"n_ran_checked":12,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":6,"phrase":"13 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/uncertainty-based-offline-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2110.01548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01548"}},"official":null}},{"url":"/paper/on-the-estimation-bias-in-double-q-learning-1","slug":"on-the-estimation-bias-in-double-q-learning-1","title":"On the Estimation Bias in Double Q-Learning","date":"2021-09-29","arxiv_id":"2109.14419","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/on-the-estimation-bias-in-double-q-learning-1#ran","syntology_url":"https://syntology.ai/paper/2109.14419","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.14419"}},"official":{"repos":["stilwell-git/doubly-bounded-q-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/catastrophic-interference-in-reinforcement","slug":"catastrophic-interference-in-reinforcement","title":"Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation","date":"2021-09-01","arxiv_id":"2109.00525","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/catastrophic-interference-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2109.00525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00525"}},"official":{"repos":["sweety-dm/interference-aware-deep-q-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/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/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/iq-learn-inverse-soft-q-learning-for","slug":"iq-learn-inverse-soft-q-learning-for","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","date":"2021-06-23","arxiv_id":"2106.12142","repositories_listed":5,"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/iq-learn-inverse-soft-q-learning-for#ran","syntology_url":"https://syntology.ai/paper/2106.12142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12142"}},"official":{"repos":["Div99/IQ-Learn"],"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/q-learning-lagrange-policies-for-multi-action","slug":"q-learning-lagrange-policies-for-multi-action","title":"Q-Learning Lagrange Policies for Multi-Action Restless Bandits","date":"2021-06-22","arxiv_id":"2106.12024","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/q-learning-lagrange-policies-for-multi-action#ran","syntology_url":"https://syntology.ai/paper/2106.12024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12024"}},"official":{"repos":["killian-34/MAIQL_and_LPQL"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":3,"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/temporl-learning-when-to-act","slug":"temporl-learning-when-to-act","title":"TempoRL: Learning When to Act","date":"2021-06-09","arxiv_id":"2106.05262","repositories_listed":2,"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/temporl-learning-when-to-act#ran","syntology_url":"https://syntology.ai/paper/2106.05262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05262"}},"official":{"repos":["automl/TempoRL"],"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/dfac-framework-factorizing-the-value-function","slug":"dfac-framework-factorizing-the-value-function","title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","date":"2021-02-16","arxiv_id":"2102.07936","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/dfac-framework-factorizing-the-value-function#ran","syntology_url":"https://syntology.ai/paper/2102.07936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07936"}},"official":{"repos":["j3soon/dfac"],"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/acting-in-delayed-environments-with-non-1","slug":"acting-in-delayed-environments-with-non-1","title":"Acting in Delayed Environments with Non-Stationary Markov Policies","date":"2021-01-28","arxiv_id":"2101.11992","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/acting-in-delayed-environments-with-non-1#ran","syntology_url":"https://syntology.ai/paper/2101.11992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.11992"}},"official":{"repos":["galdl/rl_delay_atari","galdl/rl_delay_basic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/randomized-ensembled-double-q-learning-1","slug":"randomized-ensembled-double-q-learning-1","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","date":"2021-01-15","arxiv_id":"2101.05982","repositories_listed":6,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/randomized-ensembled-double-q-learning-1#ran","syntology_url":"https://syntology.ai/paper/2101.05982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.05982"}},"official":{"repos":["watchernyu/REDQ"],"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/learning-guidance-rewards-with-trajectory","slug":"learning-guidance-rewards-with-trajectory","title":"Learning Guidance Rewards with Trajectory-space Smoothing","date":"2020-10-23","arxiv_id":"2010.12718","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-guidance-rewards-with-trajectory#ran","syntology_url":"https://syntology.ai/paper/2010.12718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.12718"}},"official":{"repos":["tgangwani/GuidanceRewards"],"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/q-learning-with-language-model-for-edit-based","slug":"q-learning-with-language-model-for-edit-based","title":"Q-learning with Language Model for Edit-based Unsupervised Summarization","date":"2020-10-09","arxiv_id":"2010.04379","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/q-learning-with-language-model-for-edit-based#ran","syntology_url":"https://syntology.ai/paper/2010.04379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04379"}},"official":{"repos":["kohilin/ealm"],"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/robust-deep-reinforcement-learning-through","slug":"robust-deep-reinforcement-learning-through","title":"Robust Deep Reinforcement Learning through Adversarial Loss","date":"2020-08-05","arxiv_id":"2008.01976","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-deep-reinforcement-learning-through#ran","syntology_url":"https://syntology.ai/paper/2008.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01976"}},"official":{"repos":["tuomaso/radial_rl","tuomaso/radial_rl_v2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/qplex-duplex-dueling-multi-agent-q-learning","slug":"qplex-duplex-dueling-multi-agent-q-learning","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","date":"2020-08-03","arxiv_id":"2008.01062","repositories_listed":6,"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/qplex-duplex-dueling-multi-agent-q-learning#ran","syntology_url":"https://syntology.ai/paper/2008.01062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01062"}},"official":{"repos":["wjh720/QPLEX"],"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/pc-pg-policy-cover-directed-exploration-for","slug":"pc-pg-policy-cover-directed-exploration-for","title":"PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning","date":"2020-07-16","arxiv_id":"2007.08459","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pc-pg-policy-cover-directed-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2007.08459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08459"}},"official":null}},{"url":"/paper/revisiting-fundamentals-of-experience-replay","slug":"revisiting-fundamentals-of-experience-replay","title":"Revisiting Fundamentals of Experience Replay","date":"2020-07-13","arxiv_id":"2007.06700","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/revisiting-fundamentals-of-experience-replay#ran","syntology_url":"https://syntology.ai/paper/2007.06700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06700"}},"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/provably-efficient-double-q-learning","slug":"provably-efficient-double-q-learning","title":"The Mean-Squared Error of Double Q-Learning","date":"2020-07-09","arxiv_id":"2007.05034","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/provably-efficient-double-q-learning#ran","syntology_url":"https://syntology.ai/paper/2007.05034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.05034"}},"official":{"repos":["wentaoweng/The-Mean-Squared-Error-of-Double-Q-Learning"],"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/gradient-temporal-difference-learning-with","slug":"gradient-temporal-difference-learning-with","title":"Gradient Temporal-Difference Learning with Regularized Corrections","date":"2020-07-01","arxiv_id":"2007.00611","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/gradient-temporal-difference-learning-with#ran","syntology_url":"https://syntology.ai/paper/2007.00611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.00611"}},"official":{"repos":["rlai-lab/Regularized-GradientTD"],"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/self-imitation-learning-via-generalized-lower","slug":"self-imitation-learning-via-generalized-lower","title":"Self-Imitation Learning via Generalized Lower Bound Q-learning","date":"2020-06-12","arxiv_id":"2006.07442","repositories_listed":0,"syntology":{"n":20,"n_ran":16,"n_constructed":4,"n_ran_checked":13,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":11,"n_pointer_only":11,"phrase":"16 ran (of which 4 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 2 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/self-imitation-learning-via-generalized-lower#ran","syntology_url":"https://syntology.ai/paper/2006.07442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07442"}},"official":null}},{"url":"/paper/conservative-q-learning-for-offline","slug":"conservative-q-learning-for-offline","title":"Conservative Q-Learning for Offline Reinforcement Learning","date":"2020-06-08","arxiv_id":"2006.04779","repositories_listed":18,"syntology":{"n":34,"n_ran":31,"n_constructed":5,"n_ran_checked":28,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":26,"n_pointer_only":19,"phrase":"31 ran (of which 5 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/conservative-q-learning-for-offline#ran","syntology_url":"https://syntology.ai/paper/2006.04779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04779"}},"official":{"repos":["aviralkumar2907/CQL"],"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-agent-determinantal-q-learning","slug":"multi-agent-determinantal-q-learning","title":"Multi-Agent Determinantal Q-Learning","date":"2020-06-02","arxiv_id":"2006.01482","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/multi-agent-determinantal-q-learning#ran","syntology_url":"https://syntology.ai/paper/2006.01482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.01482"}},"official":{"repos":["QDPP-GitHub/QDPP"],"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/spatial-action-maps-for-mobile-manipulation","slug":"spatial-action-maps-for-mobile-manipulation","title":"Spatial Action Maps for Mobile Manipulation","date":"2020-04-20","arxiv_id":"2004.09141","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spatial-action-maps-for-mobile-manipulation#ran","syntology_url":"https://syntology.ai/paper/2004.09141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.09141"}},"official":{"repos":["jimmyyhwu/spatial-action-maps"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/discor-corrective-feedback-in-reinforcement","slug":"discor-corrective-feedback-in-reinforcement","title":"DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction","date":"2020-03-16","arxiv_id":"2003.07305","repositories_listed":4,"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":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) · 1 unverified","sample_list":"/paper/discor-corrective-feedback-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2003.07305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07305"}},"official":null}},{"url":"/paper/deep-multi-agent-reinforcement-learning-for","slug":"deep-multi-agent-reinforcement-learning-for","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","date":"2020-03-14","arxiv_id":"2003.06709","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-multi-agent-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.06709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06709"}},"official":{"repos":["schroederdewitt/multiagent_mujoco"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/optimistic-exploration-even-with-a-1","slug":"optimistic-exploration-even-with-a-1","title":"Optimistic Exploration even with a Pessimistic Initialisation","date":"2020-02-26","arxiv_id":"2002.12174","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/optimistic-exploration-even-with-a-1#ran","syntology_url":"https://syntology.ai/paper/2002.12174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12174"}},"official":{"repos":["oxwhirl/opiq"],"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/bail-best-action-imitation-learning-for-batch-1","slug":"bail-best-action-imitation-learning-for-batch-1","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","date":"2019-10-27","arxiv_id":"1910.12179","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bail-best-action-imitation-learning-for-batch-1#ran","syntology_url":"https://syntology.ai/paper/1910.12179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12179"}},"official":{"repos":["lanyavik/BAIL"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/zpd-teaching-strategies-for-deep","slug":"zpd-teaching-strategies-for-deep","title":"ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations","date":"2019-10-26","arxiv_id":"1910.12154","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/zpd-teaching-strategies-for-deep#ran","syntology_url":"https://syntology.ai/paper/1910.12154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12154"}},"official":null}},{"url":"/paper/seed-rl-scalable-and-efficient-deep-rl-with-1","slug":"seed-rl-scalable-and-efficient-deep-rl-with-1","title":"SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference","date":"2019-10-15","arxiv_id":"1910.06591","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/seed-rl-scalable-and-efficient-deep-rl-with-1#ran","syntology_url":"https://syntology.ai/paper/1910.06591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06591"}},"official":{"repos":["google-research/seed_rl"],"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/meta-q-learning","slug":"meta-q-learning","title":"Meta-Q-Learning","date":"2019-09-30","arxiv_id":"1910.00125","repositories_listed":2,"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/meta-q-learning#ran","syntology_url":"https://syntology.ai/paper/1910.00125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.00125"}},"official":{"repos":["amazon-research/meta-q-learning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/rlpyt-a-research-code-base-for-deep","slug":"rlpyt-a-research-code-base-for-deep","title":"rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch","date":"2019-09-03","arxiv_id":"1909.01500","repositories_listed":9,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/rlpyt-a-research-code-base-for-deep#ran","syntology_url":"https://syntology.ai/paper/1909.01500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.01500"}},"official":{"repos":["astooke/rlpyt"],"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/learn-how-to-cook-a-new-recipe-in-a-new-house","slug":"learn-how-to-cook-a-new-recipe-in-a-new-house","title":"Learn How to Cook a New Recipe in a New House: Using Map Familiarization, Curriculum Learning, and Bandit Feedback to Learn Families of Text-Based Adventure Games","date":"2019-08-13","arxiv_id":"1908.04777","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/learn-how-to-cook-a-new-recipe-in-a-new-house#ran","syntology_url":"https://syntology.ai/paper/1908.04777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.04777"}},"official":{"repos":["yinxusen/deepword"],"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/way-off-policy-batch-deep-reinforcement","slug":"way-off-policy-batch-deep-reinforcement","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","date":"2019-06-30","arxiv_id":"1907.00456","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/way-off-policy-batch-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1907.00456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.00456"}},"official":{"repos":["natashamjaques/neural_chat"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-empathic-deep-q-learning","slug":"towards-empathic-deep-q-learning","title":"Towards Empathic Deep Q-Learning","date":"2019-06-26","arxiv_id":"1906.10918","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/towards-empathic-deep-q-learning#ran","syntology_url":"https://syntology.ai/paper/1906.10918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.10918"}},"official":{"repos":["bartbussmann/EmpathicDQN"],"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/boosting-soft-actor-critic-emphasizing-recent","slug":"boosting-soft-actor-critic-emphasizing-recent","title":"Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past","date":"2019-06-10","arxiv_id":"1906.04009","repositories_listed":3,"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/boosting-soft-actor-critic-emphasizing-recent#ran","syntology_url":"https://syntology.ai/paper/1906.04009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04009"}},"official":null}},{"url":"/paper/reinforcement-learning-with-low-complexity","slug":"reinforcement-learning-with-low-complexity","title":"Reinforcement Learning with Low-Complexity Liquid State Machines","date":"2019-06-04","arxiv_id":"1906.01695","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/reinforcement-learning-with-low-complexity#ran","syntology_url":"https://syntology.ai/paper/1906.01695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.01695"}},"official":{"repos":["wponghiran/lsm-rl"],"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/190600949","slug":"190600949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","date":"2019-06-03","arxiv_id":"1906.00949","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/190600949#ran","syntology_url":"https://syntology.ai/paper/1906.00949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.00949"}},"official":null}},{"url":"/paper/solving-np-hard-problems-on-graphs-by","slug":"solving-np-hard-problems-on-graphs-by","title":"Solving NP-Hard Problems on Graphs with Extended AlphaGo Zero","date":"2019-05-28","arxiv_id":"1905.11623","repositories_listed":2,"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/solving-np-hard-problems-on-graphs-by#ran","syntology_url":"https://syntology.ai/paper/1905.11623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11623"}},"official":null}},{"url":"/paper/finite-time-analysis-of-q-learning-with","slug":"finite-time-analysis-of-q-learning-with","title":"Finite-Sample Analysis of Nonlinear Stochastic Approximation with Applications in Reinforcement Learning","date":"2019-05-27","arxiv_id":"1905.11425","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/finite-time-analysis-of-q-learning-with#ran","syntology_url":"https://syntology.ai/paper/1905.11425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11425"}},"official":null}},{"url":"/paper/multi-agent-deep-reinforcement-learning-for-2","slug":"multi-agent-deep-reinforcement-learning-for-2","title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","date":"2019-03-11","arxiv_id":"1903.04527","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-agent-deep-reinforcement-learning-for-2#ran","syntology_url":"https://syntology.ai/paper/1903.04527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.04527"}},"official":{"repos":["cts198859/deeprl_signal_control"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/diagnosing-bottlenecks-in-deep-q-learning","slug":"diagnosing-bottlenecks-in-deep-q-learning","title":"Diagnosing Bottlenecks in Deep Q-learning Algorithms","date":"2019-02-26","arxiv_id":"1902.10250","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/diagnosing-bottlenecks-in-deep-q-learning#ran","syntology_url":"https://syntology.ai/paper/1902.10250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.10250"}},"official":null}},{"url":"/paper/making-deep-q-learning-methods-robust-to-time","slug":"making-deep-q-learning-methods-robust-to-time","title":"Making Deep Q-learning methods robust to time discretization","date":"2019-01-28","arxiv_id":"1901.09732","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/making-deep-q-learning-methods-robust-to-time#ran","syntology_url":"https://syntology.ai/paper/1901.09732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.09732"}},"official":null}},{"url":"/paper/provably-efficient-rl-with-rich-observations","slug":"provably-efficient-rl-with-rich-observations","title":"Provably efficient RL with Rich Observations via Latent State Decoding","date":"2019-01-25","arxiv_id":"1901.09018","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/provably-efficient-rl-with-rich-observations#ran","syntology_url":"https://syntology.ai/paper/1901.09018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.09018"}},"official":{"repos":["Microsoft/StateDecoding"],"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"]}}}],"record_sha256":"90080d802bf79accca492ed89592f5a19b287013881a43a1ed15065b81afb6f0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}