{"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":"/method/q-learning/papers/ran/1","list_of":"/method/q-learning","method":"Q-Learning","archive":{"snapshot":"2025-07-28"},"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 isolate this method inside it.","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":126,"counts":{"archive_papers_tagged":1734,"with_a_code_link":464,"where_syntology_ran_a_sample":126,"not_listed_spam_title":0,"listed":1734,"listed_where_code_ran":126,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":105,"every_run_a_failure_of_syntologys_instrument":21,"listed_with_a_run_with_no_instrument_failure":105,"listed_every_run_a_failure_of_syntologys_instrument":21,"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":"/method/q-learning/papers/ran/1","prev":null,"next":"/method/q-learning/papers/ran/2","papers":[{"paper":"/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","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":4,"n_instrument":1,"unverified":3,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/paper/flow-q-learning","slug":"flow-q-learning","title":"Flow Q-Learning","date":"2025-02-04","arxiv_id":"2502.02538","n_code_links":2,"syntology":{"ran":5,"of":7,"n_ran_checked":4,"n_instrument":1,"unverified":2,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":10,"of":24,"n_ran_checked":10,"n_instrument":0,"unverified":14,"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","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"]}}},{"paper":"/paper/beyond-the-rainbow-high-performance-deep","slug":"beyond-the-rainbow-high-performance-deep","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","date":"2024-11-06","arxiv_id":"2411.03820","n_code_links":3,"syntology":{"ran":16,"of":25,"n_ran_checked":13,"n_instrument":3,"unverified":9,"pointer_only":21,"phrase":"16 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","official":{"repos":["viptankz/btr"],"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":["listed","official"]}}},{"paper":"/paper/cale-continuous-arcade-learning-environment","slug":"cale-continuous-arcade-learning-environment","title":"CALE: Continuous Arcade Learning Environment","date":"2024-10-31","arxiv_id":"2410.23810","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["farama-foundation/arcade-learning-environment"],"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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/paper/efficient-and-private-marginal-reconstruction","slug":"efficient-and-private-marginal-reconstruction","title":"Efficient and Private Marginal Reconstruction with Local Non-Negativity","date":"2024-10-01","arxiv_id":"2410.01091","n_code_links":1,"syntology":{"ran":17,"of":25,"n_ran_checked":12,"n_instrument":5,"unverified":8,"pointer_only":25,"phrase":"17 ran (of which 2 constructed an object rather than computing a result; 12 with no instrument failure: 10 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified","official":{"repos":["bcmullins/efficient-marginal-reconstruction"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":2,"n_ran_no_instrument_failure":12,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":9,"n_instrument":4,"unverified":1,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":17,"of":20,"n_ran_checked":11,"n_instrument":6,"unverified":3,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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","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"]}}},{"paper":"/paper/improving-token-based-world-models-with","slug":"improving-token-based-world-models-with","title":"Improving Token-Based World Models with Parallel Observation Prediction","date":"2024-02-08","arxiv_id":"2402.05643","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":9,"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) · 1 unverified","official":{"repos":["leor-c/rem"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/compound-returns-reduce-variance-in","slug":"compound-returns-reduce-variance-in","title":"Averaging $n$-step Returns Reduces Variance in Reinforcement Learning","date":"2024-02-06","arxiv_id":"2402.03903","n_code_links":0,"syntology":{"ran":5,"of":8,"n_ran_checked":4,"n_instrument":1,"unverified":3,"pointer_only":6,"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","official":null}},{"paper":"/paper/hyperagent-a-simple-scalable-efficient-and","slug":"hyperagent-a-simple-scalable-efficient-and","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","date":"2024-02-05","arxiv_id":"2402.10228","n_code_links":3,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["szrlee/hyperagent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":0,"n_instrument":2,"unverified":3,"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","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"]}}},{"paper":"/paper/adsorbrl-deep-multi-objective-reinforcement","slug":"adsorbrl-deep-multi-objective-reinforcement","title":"AdsorbRL: Deep Multi-Objective Reinforcement Learning for Inverse Catalysts Design","date":"2023-12-04","arxiv_id":"2312.02308","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["rlacombe/adsorbrl"],"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"]}}},{"paper":"/paper/reinforcement-learning-for-wildfire","slug":"reinforcement-learning-for-wildfire","title":"Reinforcement Learning for Wildfire Mitigation in Simulated Disaster Environments","date":"2023-11-27","arxiv_id":"2311.15925","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["mitrefireline/simfire"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/selectively-sharing-experiences-improves","slug":"selectively-sharing-experiences-improves","title":"Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning","date":"2023-11-01","arxiv_id":"2311.00865","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["mgerstgrasser/super"],"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"]}}},{"paper":"/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","n_code_links":0,"syntology":{"ran":5,"of":10,"n_ran_checked":3,"n_instrument":2,"unverified":5,"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","official":null}},{"paper":"/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","n_code_links":2,"syntology":{"ran":5,"of":9,"n_ran_checked":3,"n_instrument":2,"unverified":4,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":4,"n_instrument":3,"unverified":2,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"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","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"]}}},{"paper":"/paper/h-tsp-hierarchically-solving-the-large-scale","slug":"h-tsp-hierarchically-solving-the-large-scale","title":"H-TSP: Hierarchically Solving the Large-Scale Travelling Salesman Problem","date":"2023-04-19","arxiv_id":"2304.09395","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Learning4Optimization-HUST/H-TSP"],"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"]}}},{"paper":"/paper/modeling-moral-choices-in-social-dilemmas","slug":"modeling-moral-choices-in-social-dilemmas","title":"Modeling Moral Choices in Social Dilemmas with Multi-Agent Reinforcement Learning","date":"2023-01-20","arxiv_id":"2301.08491","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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","official":{"repos":["liza-tennant/moral_choice_dyadic","Liza-Tennant/modeling_moral_choice_dyadic"],"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"]}}},{"paper":"/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","n_code_links":4,"syntology":{"ran":8,"of":13,"n_ran_checked":5,"n_instrument":3,"unverified":5,"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","official":null}},{"paper":"/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","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/paper/applying-deep-reinforcement-learning-to-the","slug":"applying-deep-reinforcement-learning-to-the","title":"Applying Deep Reinforcement Learning to the HP Model for Protein Structure Prediction","date":"2022-11-27","arxiv_id":"2211.14939","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":11,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["compsoftmatterbiophysics-cityu-hk/applying-drl-to-hp-model-for-protein-structure-prediction"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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","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"]}}},{"paper":"/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","n_code_links":3,"syntology":{"ran":11,"of":18,"n_ran_checked":11,"n_instrument":0,"unverified":7,"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","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"]}}},{"paper":"/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","n_code_links":2,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"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","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"]}}},{"paper":"/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","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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","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"]}}},{"paper":"/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","n_code_links":3,"syntology":{"ran":13,"of":16,"n_ran_checked":13,"n_instrument":0,"unverified":3,"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","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"]}}},{"paper":"/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","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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","official":null}},{"paper":"/paper/efficient-reward-poisoning-attacks-on-online","slug":"efficient-reward-poisoning-attacks-on-online","title":"Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning","date":"2022-05-30","arxiv_id":"2205.14842","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":{"repos":["yinglunxu/reward_poisoning_attack_drl"],"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"]}}},{"paper":"/paper/epida-an-easy-plug-in-data-augmentation","slug":"epida-an-easy-plug-in-data-augmentation","title":"EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text Classification","date":"2022-04-24","arxiv_id":"2204.11205","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["zhaominyiz/epida"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/paper/deep-q-network-with-proximal-iteration-1","slug":"deep-q-network-with-proximal-iteration-1","title":"Faster Deep Reinforcement Learning with Slower Online Network","date":"2021-12-10","arxiv_id":"2112.05848","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["amazon-research/fast-rl-with-slow-updates"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"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","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"]}}},{"paper":"/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","n_code_links":5,"syntology":{"ran":13,"of":21,"n_ran_checked":12,"n_instrument":1,"unverified":8,"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","official":null}},{"paper":"/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","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"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","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"]}}},{"paper":"/paper/memory-semantization-through-perturbed-and","slug":"memory-semantization-through-perturbed-and","title":"Learning cortical representations through perturbed and adversarial dreaming","date":"2021-09-09","arxiv_id":"2109.04261","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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","official":{"repos":["NicoZenith/PAD"],"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"]}}},{"paper":"/paper/deep-reinforcement-learning-at-the-edge-of","slug":"deep-reinforcement-learning-at-the-edge-of","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","date":"2021-08-30","arxiv_id":"2108.13264","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/rliable"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":14,"of":17,"n_ran_checked":14,"n_instrument":0,"unverified":3,"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","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"]}}},{"paper":"/paper/vision-language-navigation-with-random","slug":"vision-language-navigation-with-random","title":"Vision-Language Navigation with Random Environmental Mixup","date":"2021-06-15","arxiv_id":"2106.07876","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":0,"n_instrument":1,"unverified":3,"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) · 3 unverified","official":{"repos":["lcfractal/vlnrem"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/paper/douzero-mastering-doudizhu-with-self-play","slug":"douzero-mastering-doudizhu-with-self-play","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","date":"2021-06-11","arxiv_id":"2106.06135","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":2,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["kwai/DouZero"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"paper":"/paper/adapting-to-reward-progressivity-via-spectral-1","slug":"adapting-to-reward-progressivity-via-spectral-1","title":"Adapting to Reward Progressivity via Spectral Reinforcement Learning","date":"2021-04-29","arxiv_id":"2104.14138","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["mchldann/SpectralDQN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/recurrent-rational-networks","slug":"recurrent-rational-networks","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","date":"2021-02-18","arxiv_id":"2102.09407","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":0,"n_instrument":6,"unverified":0,"pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ml-research/rational_activations","ml-research/rational_rl","ml-research/rational_sl","k4ntz/activation-functions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":2,"syntology":{"ran":3,"of":7,"n_ran_checked":1,"n_instrument":2,"unverified":4,"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","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"]}}},{"paper":"/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","n_code_links":6,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"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","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"]}}},{"paper":"/paper/reinforcement-learning-with-latent-flow-1","slug":"reinforcement-learning-with-latent-flow-1","title":"Reinforcement Learning with Latent Flow","date":"2021-01-06","arxiv_id":"2101.01857","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["WendyShang/flare","WendyShang/dqn_zoo"],"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"]}}},{"paper":"/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","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":6,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":5,"n_instrument":1,"unverified":3,"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","official":null}},{"paper":"/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","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":0,"syntology":{"ran":16,"of":20,"n_ran_checked":13,"n_instrument":3,"unverified":4,"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","official":null}},{"paper":"/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","n_code_links":18,"syntology":{"ran":31,"of":34,"n_ran_checked":28,"n_instrument":3,"unverified":3,"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","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"]}}},{"paper":"/paper/local-and-global-explanations-of-agent","slug":"local-and-global-explanations-of-agent","title":"Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Maps","date":"2020-05-18","arxiv_id":"2005.08874","n_code_links":1,"syntology":{"ran":9,"of":15,"n_ran_checked":9,"n_instrument":0,"unverified":6,"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) · 6 unverified","official":{"repos":["HuTobias/HIGHLIGHTS-LRP"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":4,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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","official":null}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/paper/interpretable-end-to-end-urban-autonomous","slug":"interpretable-end-to-end-urban-autonomous","title":"Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning","date":"2020-01-23","arxiv_id":"2001.08726","n_code_links":4,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["cjy1992/interp-e2e-driving"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/slm-lab-a-comprehensive-benchmark-and-modular-1","slug":"slm-lab-a-comprehensive-benchmark-and-modular-1","title":"SLM Lab: A Comprehensive Benchmark and Modular Software Framework for Reproducible Deep Reinforcement Learning","date":"2019-12-28","arxiv_id":"1912.12482","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["kengz/SLM-Lab"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":1,"n_instrument":4,"unverified":1,"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","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"]}}},{"paper":"/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","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"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","official":null}},{"paper":"/paper/meta-q-learning","slug":"meta-q-learning","title":"Meta-Q-Learning","date":"2019-09-30","arxiv_id":"1910.00125","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","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"]}}},{"paper":"/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","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":null}},{"paper":"/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","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"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","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"]}}},{"paper":"/paper/190600949","slug":"190600949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","date":"2019-06-03","arxiv_id":"1906.00949","n_code_links":3,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"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","official":null}},{"paper":"/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","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":null}},{"paper":"/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","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":null}},{"paper":"/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","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":6,"n_instrument":1,"unverified":2,"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","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"]}}},{"paper":"/paper/minatar-an-atari-inspired-testbed-for-more","slug":"minatar-an-atari-inspired-testbed-for-more","title":"MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments","date":"2019-03-07","arxiv_id":"1903.03176","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"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","official":{"repos":["kenjyoung/MinAtar"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"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","official":null}},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":null}},{"paper":"/paper/deep-reinforcement-learning-for-imbalanced","slug":"deep-reinforcement-learning-for-imbalanced","title":"Deep Reinforcement Learning for Imbalanced Classification","date":"2019-01-05","arxiv_id":"1901.01379","n_code_links":3,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"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","official":{"repos":["linenus/DRL-For-imbalanced-Classification"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"record_sha256":"f4b88289fd5c7abfee6ebf0ba1e7b2ed9ae4e6538a9b2a2dd9d1dfff594ab1ae","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}