{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/reinforcement-learning/papers/17","list_of":"/task/reinforcement-learning","task":"Reinforcement 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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":17,"pages_in_order":132,"rows_per_page":100,"rows":[1601,1700],"of":13178,"counts":{"archive_papers_tagged":13178,"with_a_code_link":4183,"where_syntology_ran_a_sample":1175,"not_listed_spam_title":0,"listed":13178,"listed_where_code_ran":1175,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":988,"every_run_a_failure_of_syntologys_instrument":187,"listed_with_a_run_with_no_instrument_failure":988,"listed_every_run_a_failure_of_syntologys_instrument":187,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/reinforcement-learning","prev":"/task/reinforcement-learning/papers/16","next":"/task/reinforcement-learning/papers/18","papers":[{"url":"/paper/deployable-reinforcement-learning-with","slug":"deployable-reinforcement-learning-with","title":"Deployable Reinforcement Learning with Variable Control Rate","date":"2024-01-17","arxiv_id":"2401.09286","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deployable-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2401.09286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09286"}},"official":{"repos":["alpaficia/SEAC_Pytorch_release"],"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/sharing-knowledge-in-multi-task-deep-1","slug":"sharing-knowledge-in-multi-task-deep-1","title":"Sharing Knowledge in Multi-Task Deep Reinforcement Learning","date":"2024-01-17","arxiv_id":"2401.09561","repositories_listed":1,"syntology":null},{"url":"/paper/aquarium-a-comprehensive-framework-for","slug":"aquarium-a-comprehensive-framework-for","title":"Aquarium: A Comprehensive Framework for Exploring Predator-Prey Dynamics through Multi-Agent Reinforcement Learning Algorithms","date":"2024-01-13","arxiv_id":"2401.07056","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-reinforcement-learning-with-a","slug":"personalized-reinforcement-learning-with-a","title":"Personalized Reinforcement Learning with a Budget of Policies","date":"2024-01-12","arxiv_id":"2401.06514","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-concept-bottlenecks-to-align","slug":"interpretable-concept-bottlenecks-to-align","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","date":"2024-01-11","arxiv_id":"2401.05821","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/interpretable-concept-bottlenecks-to-align#ran","syntology_url":"https://syntology.ai/paper/2401.05821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05821"}},"official":{"repos":["k4ntz/scobots"],"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/safe-reinforcement-learning-in-uncertain","slug":"safe-reinforcement-learning-in-uncertain","title":"Safe reinforcement learning in uncertain contexts","date":"2024-01-11","arxiv_id":"2401.05876","repositories_listed":1,"syntology":null},{"url":"/paper/the-distributional-reward-critic-architecture","slug":"the-distributional-reward-critic-architecture","title":"The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards","date":"2024-01-11","arxiv_id":"2401.05710","repositories_listed":1,"syntology":null},{"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/policy-regularized-offline-multi-objective","slug":"policy-regularized-offline-multi-objective","title":"Policy-regularized Offline Multi-objective Reinforcement Learning","date":"2024-01-04","arxiv_id":"2401.02244","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"8 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/policy-regularized-offline-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2401.02244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02244"}},"official":{"repos":["qianlin04/prmorl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/data-assimilation-in-chaotic-systems-using","slug":"data-assimilation-in-chaotic-systems-using","title":"Data Assimilation in Chaotic Systems Using Deep Reinforcement Learning","date":"2024-01-01","arxiv_id":"2401.00916","repositories_listed":1,"syntology":null},{"url":"/paper/ensemble-diversity-facilitates-adversarial","slug":"ensemble-diversity-facilitates-adversarial","title":"Ensemble Diversity Facilitates Adversarial Transferability","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improving-unsupervised-hierarchical","slug":"improving-unsupervised-hierarchical","title":"Improving Unsupervised Hierarchical Representation with Reinforcement Learning","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/online-symbolic-music-alignment-with-offline","slug":"online-symbolic-music-alignment-with-offline","title":"Online Symbolic Music Alignment with Offline Reinforcement Learning","date":"2023-12-31","arxiv_id":"2401.00466","repositories_listed":1,"syntology":null},{"url":"/paper/causal-state-distillation-for-explainable","slug":"causal-state-distillation-for-explainable","title":"Causal State Distillation for Explainable Reinforcement Learning","date":"2023-12-30","arxiv_id":"2401.00104","repositories_listed":1,"syntology":null},{"url":"/paper/can-active-sampling-reduce-causal-confusion","slug":"can-active-sampling-reduce-causal-confusion","title":"Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?","date":"2023-12-28","arxiv_id":"2312.17168","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/can-active-sampling-reduce-causal-confusion#ran","syntology_url":"https://syntology.ai/paper/2312.17168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17168"}},"official":{"repos":["gunshi/offline_active_rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generalizable-visual-reinforcement-learning","slug":"generalizable-visual-reinforcement-learning","title":"Generalizable Visual Reinforcement Learning with Segment Anything Model","date":"2023-12-28","arxiv_id":"2312.17116","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"6 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generalizable-visual-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2312.17116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17116"}},"official":{"repos":["wadiuvatzy/sam-g"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-trajectory-constrained-exploration","slug":"adaptive-trajectory-constrained-exploration","title":"Adaptive trajectory-constrained exploration strategy for deep reinforcement learning","date":"2023-12-27","arxiv_id":"2312.16456","repositories_listed":1,"syntology":null},{"url":"/paper/generalizable-task-representation-learning-1","slug":"generalizable-task-representation-learning-1","title":"Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations","date":"2023-12-26","arxiv_id":"2312.15909","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/generalizable-task-representation-learning-1#ran","syntology_url":"https://syntology.ai/paper/2312.15909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15909"}},"official":{"repos":["lamda-rl/gentle"],"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/optimistic-and-pessimistic-actor-in-rl","slug":"optimistic-and-pessimistic-actor-in-rl","title":"Efficient Reinforcement Learning via Decoupling Exploration and Utilization","date":"2023-12-26","arxiv_id":"2312.15965","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-unlearning","slug":"reinforcement-unlearning","title":"Reinforcement Unlearning","date":"2023-12-26","arxiv_id":"2312.15910","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-unlearning#ran","syntology_url":"https://syntology.ai/paper/2312.15910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15910"}},"official":{"repos":["cp-lab-uts/reinforcement-unlearning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/context-aware-communication-for-multi-agent","slug":"context-aware-communication-for-multi-agent","title":"Context-aware Communication for Multi-agent Reinforcement Learning","date":"2023-12-25","arxiv_id":"2312.15600","repositories_listed":1,"syntology":null},{"url":"/paper/xuance-a-comprehensive-and-unified-deep","slug":"xuance-a-comprehensive-and-unified-deep","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","date":"2023-12-25","arxiv_id":"2312.16248","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/xuance-a-comprehensive-and-unified-deep#ran","syntology_url":"https://syntology.ai/paper/2312.16248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16248"}},"official":{"repos":["agi-brain/xuance"],"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/iterative-prompt-relabeling-for-diffusion","slug":"iterative-prompt-relabeling-for-diffusion","title":"Learning from Mistakes: Iterative Prompt Relabeling for Text-to-Image Diffusion Model Training","date":"2023-12-23","arxiv_id":"2312.16204","repositories_listed":1,"syntology":null},{"url":"/paper/critic-guided-decision-transformer-for","slug":"critic-guided-decision-transformer-for","title":"Critic-Guided Decision Transformer for Offline Reinforcement Learning","date":"2023-12-21","arxiv_id":"2312.13716","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/critic-guided-decision-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2312.13716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.13716"}},"official":{"repos":["sharkwyf/cgdt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/in-context-reinforcement-learning-for","slug":"in-context-reinforcement-learning-for","title":"In-Context Reinforcement Learning for Variable Action Spaces","date":"2023-12-20","arxiv_id":"2312.13327","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/in-context-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2312.13327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.13327"}},"official":{"repos":["corl-team/headless-ad"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/openrl-a-unified-reinforcement-learning","slug":"openrl-a-unified-reinforcement-learning","title":"OpenRL: A Unified Reinforcement Learning Framework","date":"2023-12-20","arxiv_id":"2312.16189","repositories_listed":1,"syntology":null},{"url":"/paper/rfrl-gym-a-reinforcement-learning-testbed-for","slug":"rfrl-gym-a-reinforcement-learning-testbed-for","title":"RFRL Gym: A Reinforcement Learning Testbed for Cognitive Radio Applications","date":"2023-12-20","arxiv_id":"2401.05406","repositories_listed":1,"syntology":null},{"url":"/paper/badrl-sparse-targeted-backdoor-attack-against","slug":"badrl-sparse-targeted-backdoor-attack-against","title":"BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning","date":"2023-12-19","arxiv_id":"2312.12585","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/badrl-sparse-targeted-backdoor-attack-against#ran","syntology_url":"https://syntology.ai/paper/2312.12585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12585"}},"official":{"repos":["7777777cc/code"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/emergence-of-in-context-reinforcement","slug":"emergence-of-in-context-reinforcement","title":"Emergence of In-Context Reinforcement Learning from Noise Distillation","date":"2023-12-19","arxiv_id":"2312.12275","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/emergence-of-in-context-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2312.12275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12275"}},"official":{"repos":["corl-team/ad-eps"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/investigating-the-performance-and-reliability","slug":"investigating-the-performance-and-reliability","title":"Investigating the Performance and Reliability, of the Q-Learning Algorithm in Various Unknown Environments","date":"2023-12-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sample-efficient-reinforcement-learning-with-4","slug":"sample-efficient-reinforcement-learning-with-4","title":"Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge","date":"2023-12-19","arxiv_id":"2312.12558","repositories_listed":1,"syntology":null},{"url":"/paper/challenges-for-reinforcement-learning-in-1","slug":"challenges-for-reinforcement-learning-in-1","title":"Challenges for Reinforcement Learning in Quantum Circuit Design","date":"2023-12-18","arxiv_id":"2312.11337","repositories_listed":1,"syntology":null},{"url":"/paper/colored-noise-in-ppo-improved-exploration-and","slug":"colored-noise-in-ppo-improved-exploration-and","title":"Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling","date":"2023-12-18","arxiv_id":"2312.11091","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-reinforcement-learning-agents","slug":"explaining-reinforcement-learning-agents","title":"Explaining Reinforcement Learning Agents Through Counterfactual Action Outcomes","date":"2023-12-18","arxiv_id":"2312.11118","repositories_listed":1,"syntology":null},{"url":"/paper/learning-a-diffusion-model-policy-from","slug":"learning-a-diffusion-model-policy-from","title":"Learning a Diffusion Model Policy from Rewards via Q-Score Matching","date":"2023-12-18","arxiv_id":"2312.11752","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":4,"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/learning-a-diffusion-model-policy-from#ran","syntology_url":"https://syntology.ai/paper/2312.11752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11752"}},"official":{"repos":["Alescontrela/score_matching_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/prediction-and-control-in-continual-1","slug":"prediction-and-control-in-continual-1","title":"Prediction and Control in Continual Reinforcement Learning","date":"2023-12-18","arxiv_id":"2312.11669","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/prediction-and-control-in-continual-1#ran","syntology_url":"https://syntology.ai/paper/2312.11669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11669"}},"official":{"repos":["NishanthVAnand/prediction_and_control_in_continual_reinforcement_learning"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/deriving-rewards-for-reinforcement-learning","slug":"deriving-rewards-for-reinforcement-learning","title":"Deriving Rewards for Reinforcement Learning from Symbolic Behaviour Descriptions of Bipedal Walking","date":"2023-12-16","arxiv_id":"2312.10328","repositories_listed":1,"syntology":null},{"url":"/paper/improving-environment-robustness-of-deep","slug":"improving-environment-robustness-of-deep","title":"Improving Environment Robustness of Deep Reinforcement Learning Approaches for Autonomous Racing Using Bayesian Optimization-based Curriculum Learning","date":"2023-12-16","arxiv_id":"2312.10557","repositories_listed":1,"syntology":null},{"url":"/paper/logostylefool-vitiating-video-recognition","slug":"logostylefool-vitiating-video-recognition","title":"LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer","date":"2023-12-15","arxiv_id":"2312.09935","repositories_listed":1,"syntology":null},{"url":"/paper/peer-learning-learning-complex-policies-in","slug":"peer-learning-learning-complex-policies-in","title":"Peer Learning: Learning Complex Policies in Groups from Scratch via Action Recommendations","date":"2023-12-15","arxiv_id":"2312.09950","repositories_listed":1,"syntology":null},{"url":"/paper/sample-efficient-learning-to-solve-a-real","slug":"sample-efficient-learning-to-solve-a-real","title":"Sample-Efficient Learning to Solve a Real-World Labyrinth Game Using Data-Augmented Model-Based Reinforcement Learning","date":"2023-12-15","arxiv_id":"2312.09906","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-deep-reinforcement-learning-based-3","slug":"multi-agent-deep-reinforcement-learning-based-3","title":"Multi-agent deep reinforcement learning based real-time planning approach for responsive customized bus routes","date":"2023-12-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/i-open-at-the-close-a-deep-reinforcement","slug":"i-open-at-the-close-a-deep-reinforcement","title":"I Open at the Close: A Deep Reinforcement Learning Evaluation of Open Streets Initiatives","date":"2023-12-12","arxiv_id":"2312.07680","repositories_listed":1,"syntology":null},{"url":"/paper/rerogcrl-representation-based-robustness-in","slug":"rerogcrl-representation-based-robustness-in","title":"ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning","date":"2023-12-12","arxiv_id":"2312.07392","repositories_listed":1,"syntology":null},{"url":"/paper/decoupling-meta-reinforcement-learning-with","slug":"decoupling-meta-reinforcement-learning-with","title":"Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills","date":"2023-12-11","arxiv_id":"2312.06518","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":3,"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/decoupling-meta-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2312.06518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06518"}},"official":{"repos":["hehongc/DCMRL"],"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/no-prior-mask-eliminate-redundant-action-for","slug":"no-prior-mask-eliminate-redundant-action-for","title":"No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning","date":"2023-12-11","arxiv_id":"2312.06258","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":6,"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/no-prior-mask-eliminate-redundant-action-for#ran","syntology_url":"https://syntology.ai/paper/2312.06258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06258"}},"official":{"repos":["zhongdy15/npm"],"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/reward-certification-for-policy-smoothed","slug":"reward-certification-for-policy-smoothed","title":"Reward Certification for Policy Smoothed Reinforcement Learning","date":"2023-12-11","arxiv_id":"2312.06436","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":11,"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) · 6 unverified","sample_list":"/paper/reward-certification-for-policy-smoothed#ran","syntology_url":"https://syntology.ai/paper/2312.06436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06436"}},"official":{"repos":["trustai/receps"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/the-generalization-gap-in-offline","slug":"the-generalization-gap-in-offline","title":"The Generalization Gap in Offline Reinforcement Learning","date":"2023-12-10","arxiv_id":"2312.05742","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"8 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/the-generalization-gap-in-offline#ran","syntology_url":"https://syntology.ai/paper/2312.05742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05742"}},"official":{"repos":["facebookresearch/gen_dgrl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/distributional-bellman-operators-over-mean","slug":"distributional-bellman-operators-over-mean","title":"Distributional Bellman Operators over Mean Embeddings","date":"2023-12-09","arxiv_id":"2312.07358","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-the-gaps-learning-verifiable-model","slug":"bridging-the-gaps-learning-verifiable-model","title":"MPC-Inspired Reinforcement Learning for Verifiable Model-Free Control","date":"2023-12-08","arxiv_id":"2312.05332","repositories_listed":1,"syntology":null},{"url":"/paper/codex-a-cluster-based-method-for-explainable","slug":"codex-a-cluster-based-method-for-explainable","title":"CODEX: A Cluster-Based Method for Explainable Reinforcement Learning","date":"2023-12-07","arxiv_id":"2312.04216","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-distributed-reinforcement-learning","slug":"optimizing-distributed-reinforcement-learning","title":"Efficient Parallel Reinforcement Learning Framework using the Reactor Model","date":"2023-12-07","arxiv_id":"2312.04704","repositories_listed":1,"syntology":null},{"url":"/paper/pearl-a-production-ready-reinforcement","slug":"pearl-a-production-ready-reinforcement","title":"Pearl: A Production-ready Reinforcement Learning Agent","date":"2023-12-06","arxiv_id":"2312.03814","repositories_listed":1,"syntology":null},{"url":"/paper/sdsra-a-skill-driven-skill-recombination","slug":"sdsra-a-skill-driven-skill-recombination","title":"SDSRA: A Skill-Driven Skill-Recombination Algorithm for Efficient Policy Learning","date":"2023-12-06","arxiv_id":"2312.03216","repositories_listed":1,"syntology":null},{"url":"/paper/danzero-dominating-the-guandan-game-through","slug":"danzero-dominating-the-guandan-game-through","title":"DanZero+: Dominating the GuanDan Game through Reinforcement Learning","date":"2023-12-05","arxiv_id":"2312.02561","repositories_listed":1,"syntology":null},{"url":"/paper/lexci-a-framework-for-reinforcement-learning","slug":"lexci-a-framework-for-reinforcement-learning","title":"LExCI: A Framework for Reinforcement Learning with Embedded Systems","date":"2023-12-05","arxiv_id":"2312.02739","repositories_listed":1,"syntology":null},{"url":"/paper/using-curiosity-for-an-even-representation-of","slug":"using-curiosity-for-an-even-representation-of","title":"Using Curiosity for an Even Representation of Tasks in Continual Offline Reinforcement Learning","date":"2023-12-05","arxiv_id":"2312.03177","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarl-benchmarking-multi-agent","slug":"benchmarl-benchmarking-multi-agent","title":"BenchMARL: Benchmarking Multi-Agent Reinforcement Learning","date":"2023-12-03","arxiv_id":"2312.01472","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarl-benchmarking-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2312.01472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01472"}},"official":{"repos":["facebookresearch/benchmarl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/harnessing-discrete-representations-for","slug":"harnessing-discrete-representations-for","title":"Harnessing Discrete Representations For Continual Reinforcement Learning","date":"2023-12-02","arxiv_id":"2312.01203","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/harnessing-discrete-representations-for#ran","syntology_url":"https://syntology.ai/paper/2312.01203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01203"}},"official":{"repos":["ejmejm/discrete-representations-for-continual-rl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/sample-efficient-reinforcement-learning-from","slug":"sample-efficient-reinforcement-learning-from","title":"Sample Efficient Preference Alignment in LLMs via Active Exploration","date":"2023-12-01","arxiv_id":"2312.00267","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sample-efficient-reinforcement-learning-from#ran","syntology_url":"https://syntology.ai/paper/2312.00267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00267"}},"official":{"repos":["belakaria/active-llm-alignment"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/controlgym-large-scale-safety-critical","slug":"controlgym-large-scale-safety-critical","title":"Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms","date":"2023-11-30","arxiv_id":"2311.18736","repositories_listed":1,"syntology":null},{"url":"/paper/lmrl-gym-benchmarks-for-multi-turn","slug":"lmrl-gym-benchmarks-for-multi-turn","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","date":"2023-11-30","arxiv_id":"2311.18232","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lmrl-gym-benchmarks-for-multi-turn#ran","syntology_url":"https://syntology.ai/paper/2311.18232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18232"}},"official":{"repos":["abdulhaim/lmrl-gym"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/optimal-attack-and-defense-for-reinforcement","slug":"optimal-attack-and-defense-for-reinforcement","title":"Optimal Attack and Defense for Reinforcement Learning","date":"2023-11-30","arxiv_id":"2312.00198","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-zx-diagrams-with-deep","slug":"optimizing-zx-diagrams-with-deep","title":"Optimizing ZX-Diagrams with Deep Reinforcement Learning","date":"2023-11-30","arxiv_id":"2311.18588","repositories_listed":1,"syntology":null},{"url":"/paper/predictable-reinforcement-learning-dynamics","slug":"predictable-reinforcement-learning-dynamics","title":"Predictable Reinforcement Learning Dynamics through Entropy Rate Minimization","date":"2023-11-30","arxiv_id":"2311.18703","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-replaces-supervision-query","slug":"reinforcement-replaces-supervision-query","title":"Reinforcement Replaces Supervision: Query focused Summarization using Deep Reinforcement Learning","date":"2023-11-29","arxiv_id":"2311.17514","repositories_listed":1,"syntology":null},{"url":"/paper/an-investigation-of-time-reversal-symmetry-in","slug":"an-investigation-of-time-reversal-symmetry-in","title":"An Investigation of Time Reversal Symmetry in Reinforcement Learning","date":"2023-11-28","arxiv_id":"2311.17008","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-diffusion-models-with-text-encoder","slug":"enhancing-diffusion-models-with-text-encoder","title":"Enhancing Diffusion Models with Text-Encoder Reinforcement Learning","date":"2023-11-27","arxiv_id":"2311.15657","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/enhancing-diffusion-models-with-text-encoder#ran","syntology_url":"https://syntology.ai/paper/2311.15657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15657"}},"official":{"repos":["chaofengc/texforce"],"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/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","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/reinforcement-learning-for-wildfire#ran","syntology_url":"https://syntology.ai/paper/2311.15925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15925"}},"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"]}}},{"url":"/paper/utilizing-explainability-techniques-for","slug":"utilizing-explainability-techniques-for","title":"Utilizing Explainability Techniques for Reinforcement Learning Model Assurance","date":"2023-11-27","arxiv_id":"2311.15838","repositories_listed":1,"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":7,"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/utilizing-explainability-techniques-for#ran","syntology_url":"https://syntology.ai/paper/2311.15838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15838"}},"official":{"repos":["mitre/arlin"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/margin-trader-a-reinforcement-learning","slug":"margin-trader-a-reinforcement-learning","title":"Margin Trader: A Reinforcement Learning Framework for Portfolio Management with Margin and Constraints","date":"2023-11-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/from-images-to-connections-can-dqn-with-gnns","slug":"from-images-to-connections-can-dqn-with-gnns","title":"From Images to Connections: Can DQN with GNNs learn the Strategic Game of Hex?","date":"2023-11-22","arxiv_id":"2311.13414","repositories_listed":1,"syntology":null},{"url":"/paper/replay-enhanced-continual-reinforcement","slug":"replay-enhanced-continual-reinforcement","title":"Replay-enhanced Continual Reinforcement Learning","date":"2023-11-20","arxiv_id":"2311.11557","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/replay-enhanced-continual-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2311.11557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.11557"}},"official":{"repos":["Sweety-dm/RECALL"],"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"]}}},{"url":"/paper/multi-task-reinforcement-learning-with-1","slug":"multi-task-reinforcement-learning-with-1","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","date":"2023-11-19","arxiv_id":"2311.11385","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-task-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/2311.11385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.11385"}},"official":{"repos":["AhmedMagdyHendawy/MOORE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/edugym-an-environment-suite-for-reinforcement","slug":"edugym-an-environment-suite-for-reinforcement","title":"EduGym: An Environment and Notebook Suite for Reinforcement Learning Education","date":"2023-11-17","arxiv_id":"2311.10590","repositories_listed":1,"syntology":null},{"url":"/paper/guaranteeing-control-requirements-via-reward","slug":"guaranteeing-control-requirements-via-reward","title":"Guaranteeing Control Requirements via Reward Shaping in Reinforcement Learning","date":"2023-11-16","arxiv_id":"2311.10026","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-model-predictive","slug":"reinforcement-learning-with-model-predictive","title":"Reinforcement Learning with Model Predictive Control for Highway Ramp Metering","date":"2023-11-15","arxiv_id":"2311.08820","repositories_listed":1,"syntology":null},{"url":"/paper/direct-preference-optimization-for-neural","slug":"direct-preference-optimization-for-neural","title":"Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding","date":"2023-11-14","arxiv_id":"2311.08380","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/direct-preference-optimization-for-neural#ran","syntology_url":"https://syntology.ai/paper/2311.08380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08380"}},"official":{"repos":["bruceyg/dpo-mbr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-for-solving-stochastic","slug":"reinforcement-learning-for-solving-stochastic","title":"Reinforcement Learning for Solving Stochastic Vehicle Routing Problem","date":"2023-11-13","arxiv_id":"2311.07708","repositories_listed":1,"syntology":null},{"url":"/paper/anytime-constrained-reinforcement-learning","slug":"anytime-constrained-reinforcement-learning","title":"Anytime-Constrained Reinforcement Learning","date":"2023-11-09","arxiv_id":"2311.05511","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-quantum-reinforcement-learning","slug":"multi-agent-quantum-reinforcement-learning","title":"Multi-Agent Quantum Reinforcement Learning using Evolutionary Optimization","date":"2023-11-09","arxiv_id":"2311.05546","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/multi-agent-quantum-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2311.05546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05546"}},"official":{"repos":["michaelkoelle/qmarl-evo"],"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/compilation-of-product-formula-hamiltonian","slug":"compilation-of-product-formula-hamiltonian","title":"Compilation of product-formula Hamiltonian simulation via reinforcement learning","date":"2023-11-07","arxiv_id":"2311.04285","repositories_listed":1,"syntology":null},{"url":"/paper/context-shift-reduction-for-offline-meta-1","slug":"context-shift-reduction-for-offline-meta-1","title":"Context Shift Reduction for Offline Meta-Reinforcement Learning","date":"2023-11-07","arxiv_id":"2311.03695","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/context-shift-reduction-for-offline-meta-1#ran","syntology_url":"https://syntology.ai/paper/2311.03695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03695"}},"official":{"repos":["moreanp/csro"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-fine-tuning-of","slug":"reinforcement-learning-fine-tuning-of","title":"Reinforcement Learning Fine-tuning of Language Models is Biased Towards More Extractable Features","date":"2023-11-07","arxiv_id":"2311.04046","repositories_listed":1,"syntology":null},{"url":"/paper/causal-question-answering-with-reinforcement","slug":"causal-question-answering-with-reinforcement","title":"Causal Question Answering with Reinforcement Learning","date":"2023-11-05","arxiv_id":"2311.02760","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-reinforcement-learning-for-power","slug":"hierarchical-reinforcement-learning-for-power","title":"Hierarchical Reinforcement Learning for Power Network Topology Control","date":"2023-11-03","arxiv_id":"2311.02129","repositories_listed":1,"syntology":null},{"url":"/paper/riskq-risk-sensitive-multi-agent","slug":"riskq-risk-sensitive-multi-agent","title":"RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization","date":"2023-11-03","arxiv_id":"2311.01753","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/riskq-risk-sensitive-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2311.01753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01753"}},"official":{"repos":["xmu-rl-3dv/riskq"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/state-wise-safe-reinforcement-learning-with","slug":"state-wise-safe-reinforcement-learning-with","title":"State-Wise Safe Reinforcement Learning With Pixel Observations","date":"2023-11-03","arxiv_id":"2311.02227","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":14,"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) · 2 unverified","sample_list":"/paper/state-wise-safe-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2311.02227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.02227"}},"official":{"repos":["simonzhan-code/step-wise_saferl_pixel"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastive-modules-with-temporal-attention","slug":"contrastive-modules-with-temporal-attention","title":"Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning","date":"2023-11-02","arxiv_id":"2311.01075","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":4,"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/contrastive-modules-with-temporal-attention#ran","syntology_url":"https://syntology.ai/paper/2311.01075","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01075"}},"official":{"repos":["niiceMing/CMTA"],"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/diffusion-models-for-reinforcement-learning-a","slug":"diffusion-models-for-reinforcement-learning-a","title":"Diffusion Models for Reinforcement Learning: A Survey","date":"2023-11-02","arxiv_id":"2311.01223","repositories_listed":1,"syntology":null},{"url":"/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","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/selectively-sharing-experiences-improves#ran","syntology_url":"https://syntology.ai/paper/2311.00865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.00865"}},"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"]}}},{"url":"/paper/amoeba-circumventing-ml-supported-network","slug":"amoeba-circumventing-ml-supported-network","title":"Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement Learning","date":"2023-10-31","arxiv_id":"2310.20469","repositories_listed":1,"syntology":null},{"url":"/paper/network-contention-aware-cluster-scheduling","slug":"network-contention-aware-cluster-scheduling","title":"Network Contention-Aware Cluster Scheduling with Reinforcement Learning","date":"2023-10-31","arxiv_id":"2310.20209","repositories_listed":1,"syntology":null},{"url":"/paper/variational-curriculum-reinforcement-learning","slug":"variational-curriculum-reinforcement-learning","title":"Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills","date":"2023-10-30","arxiv_id":"2310.19424","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/variational-curriculum-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2310.19424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19424"}},"official":{"repos":["seongun-kim/vcrl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-framework-for-interpretable-and","slug":"hierarchical-framework-for-interpretable-and","title":"Hierarchical Framework for Interpretable and Probabilistic Model-Based Safe Reinforcement Learning","date":"2023-10-28","arxiv_id":"2310.18811","repositories_listed":1,"syntology":null},{"url":"/paper/robust-offline-policy-evaluation-and","slug":"robust-offline-policy-evaluation-and","title":"Robust Offline Reinforcement learning with Heavy-Tailed Rewards","date":"2023-10-28","arxiv_id":"2310.18715","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-offline-policy-evaluation-and#ran","syntology_url":"https://syntology.ai/paper/2310.18715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18715"}},"official":{"repos":["mamba413/room"],"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/hyperparameter-optimization-for-multi","slug":"hyperparameter-optimization-for-multi","title":"Hyperparameter Optimization for Multi-Objective Reinforcement Learning","date":"2023-10-25","arxiv_id":"2310.16487","repositories_listed":1,"syntology":null},{"url":"/paper/model-predictive-control-based-value","slug":"model-predictive-control-based-value","title":"Model predictive control-based value estimation for efficient reinforcement learning","date":"2023-10-25","arxiv_id":"2310.16646","repositories_listed":1,"syntology":null},{"url":"/paper/uav-pathfinding-in-dynamic-obstacle-avoidance","slug":"uav-pathfinding-in-dynamic-obstacle-avoidance","title":"Multi-Agent Reinforcement Learning-Based UAV Pathfinding for Obstacle Avoidance in Stochastic Environment","date":"2023-10-25","arxiv_id":"2310.16659","repositories_listed":1,"syntology":null},{"url":"/paper/corruption-robust-offline-reinforcement-2","slug":"corruption-robust-offline-reinforcement-2","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","date":"2023-10-23","arxiv_id":"2310.14550","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":0,"n_no_contract":2,"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, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/corruption-robust-offline-reinforcement-2#ran","syntology_url":"https://syntology.ai/paper/2310.14550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14550"}},"official":{"repos":["yangrui2015/uwmsg"],"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"]}}}],"record_sha256":"44b9fb3d3eea6ecd0eda051295e1689980680a6fef20780cb60c98d8b40b3178","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}