{"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-2/papers/13","list_of":"/task/reinforcement-learning-2","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":13,"pages_in_order":135,"rows_per_page":100,"rows":[1201,1300],"of":13427,"counts":{"archive_papers_tagged":13427,"with_a_code_link":4119,"where_syntology_ran_a_sample":1165,"not_listed_spam_title":0,"listed":13427,"listed_where_code_ran":1165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":973,"every_run_a_failure_of_syntologys_instrument":192,"listed_with_a_run_with_no_instrument_failure":973,"listed_every_run_a_failure_of_syntologys_instrument":192,"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-2","prev":"/task/reinforcement-learning-2/papers/12","next":"/task/reinforcement-learning-2/papers/14","papers":[{"url":"/paper/craftium-an-extensible-framework-for-creating","slug":"craftium-an-extensible-framework-for-creating","title":"Craftium: An Extensible Framework for Creating Reinforcement Learning Environments","date":"2024-07-04","arxiv_id":"2407.03969","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"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) · 1 unverified","sample_list":"/paper/craftium-an-extensible-framework-for-creating#ran","syntology_url":"https://syntology.ai/paper/2407.03969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03969"}},"official":{"repos":["mikelma/craftium"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/q-adapter-training-your-llm-adapter-as-a","slug":"q-adapter-training-your-llm-adapter-as-a","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","date":"2024-07-04","arxiv_id":"2407.03856","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/q-adapter-training-your-llm-adapter-as-a#ran","syntology_url":"https://syntology.ai/paper/2407.03856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03856"}},"official":{"repos":["mansicer/Q-Adapter"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/robocupgym-a-challenging-continuous-control","slug":"robocupgym-a-challenging-continuous-control","title":"RobocupGym: A challenging continuous control benchmark in Robocup","date":"2024-07-03","arxiv_id":"2407.14516","repositories_listed":1,"syntology":null},{"url":"/paper/value-penalized-auxiliary-control-from","slug":"value-penalized-auxiliary-control-from","title":"Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples","date":"2024-07-03","arxiv_id":"2407.03311","repositories_listed":1,"syntology":null},{"url":"/paper/generation-of-geodesics-with-actor-critic","slug":"generation-of-geodesics-with-actor-critic","title":"Generation of Geodesics with Actor-Critic Reinforcement Learning to Predict Midpoints","date":"2024-07-02","arxiv_id":"2407.01991","repositories_listed":1,"syntology":null},{"url":"/paper/weight-clipping-for-deep-continual-and","slug":"weight-clipping-for-deep-continual-and","title":"Weight Clipping for Deep Continual and Reinforcement Learning","date":"2024-07-01","arxiv_id":"2407.01704","repositories_listed":1,"syntology":null},{"url":"/paper/model-free-active-exploration-in-1","slug":"model-free-active-exploration-in-1","title":"Model-Free Active Exploration in Reinforcement Learning","date":"2024-06-30","arxiv_id":"2407.00801","repositories_listed":1,"syntology":null},{"url":"/paper/a-two-stage-reinforcement-learning-based","slug":"a-two-stage-reinforcement-learning-based","title":"A Two-stage Reinforcement Learning-based Approach for Multi-entity Task Allocation","date":"2024-06-29","arxiv_id":"2407.00496","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-constant-negative-rewards-for-goal","slug":"revisiting-constant-negative-rewards-for-goal","title":"Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning","date":"2024-06-29","arxiv_id":"2407.00324","repositories_listed":1,"syntology":null},{"url":"/paper/external-model-motivated-agents-reinforcement","slug":"external-model-motivated-agents-reinforcement","title":"External Model Motivated Agents: Reinforcement Learning for Enhanced Environment Sampling","date":"2024-06-28","arxiv_id":"2407.00264","repositories_listed":1,"syntology":null},{"url":"/paper/operator-world-models-for-reinforcement","slug":"operator-world-models-for-reinforcement","title":"Operator World Models for Reinforcement Learning","date":"2024-06-28","arxiv_id":"2406.19861","repositories_listed":1,"syntology":null},{"url":"/paper/bidirectional-reachable-hierarchical","slug":"bidirectional-reachable-hierarchical","title":"Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies","date":"2024-06-26","arxiv_id":"2406.18053","repositories_listed":1,"syntology":null},{"url":"/paper/domain-adaptation-of-echocardiography","slug":"domain-adaptation-of-echocardiography","title":"Domain Adaptation of Echocardiography Segmentation Via Reinforcement Learning","date":"2024-06-25","arxiv_id":"2406.17902","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-consistency-of-hyper-parameter","slug":"on-the-consistency-of-hyper-parameter","title":"On the consistency of hyper-parameter selection in value-based deep reinforcement learning","date":"2024-06-25","arxiv_id":"2406.17523","repositories_listed":1,"syntology":null},{"url":"/paper/when-does-self-prediction-help-understanding","slug":"when-does-self-prediction-help-understanding","title":"When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning","date":"2024-06-25","arxiv_id":"2406.17718","repositories_listed":1,"syntology":null},{"url":"/paper/confidence-aware-inverse-constrained","slug":"confidence-aware-inverse-constrained","title":"Confidence Aware Inverse Constrained Reinforcement Learning","date":"2024-06-24","arxiv_id":"2406.16782","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/confidence-aware-inverse-constrained#ran","syntology_url":"https://syntology.ai/paper/2406.16782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16782"}},"official":{"repos":["sriram94/confidenceawareicrl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/kehrl-learning-knowledge-enhanced-language","slug":"kehrl-learning-knowledge-enhanced-language","title":"KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement Learning","date":"2024-06-24","arxiv_id":"2406.16374","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-subgoal-representations-for","slug":"probabilistic-subgoal-representations-for","title":"Probabilistic Subgoal Representations for Hierarchical Reinforcement learning","date":"2024-06-24","arxiv_id":"2406.16707","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-via-auxiliary-task","slug":"reinforcement-learning-via-auxiliary-task","title":"Reinforcement Learning via Auxiliary Task Distillation","date":"2024-06-24","arxiv_id":"2406.17168","repositories_listed":1,"syntology":null},{"url":"/paper/bounding-box-inference-for-error-aware-model","slug":"bounding-box-inference-for-error-aware-model","title":"Bounding-Box Inference for Error-Aware Model-Based Reinforcement Learning","date":"2024-06-23","arxiv_id":"2406.16006","repositories_listed":1,"syntology":null},{"url":"/paper/sit-symmetry-invariant-transformers-for","slug":"sit-symmetry-invariant-transformers-for","title":"SiT: Symmetry-Invariant Transformers for Generalisation in Reinforcement Learning","date":"2024-06-21","arxiv_id":"2406.15025","repositories_listed":1,"syntology":null},{"url":"/paper/towards-general-negotiation-strategies-with","slug":"towards-general-negotiation-strategies-with","title":"Towards General Negotiation Strategies with End-to-End Reinforcement Learning","date":"2024-06-21","arxiv_id":"2406.15096","repositories_listed":1,"syntology":null},{"url":"/paper/a-benchmark-study-of-deep-rl-methods-for","slug":"a-benchmark-study-of-deep-rl-methods-for","title":"A Benchmark Study of Deep-RL Methods for Maximum Coverage Problems over Graphs","date":"2024-06-20","arxiv_id":"2406.14697","repositories_listed":1,"syntology":null},{"url":"/paper/macrohft-memory-augmented-context-aware","slug":"macrohft-memory-augmented-context-aware","title":"MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading","date":"2024-06-20","arxiv_id":"2406.14537","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/macrohft-memory-augmented-context-aware#ran","syntology_url":"https://syntology.ai/paper/2406.14537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14537"}},"official":{"repos":["ZONG0004/MacroHFT"],"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"]}}},{"url":"/paper/soft-qmix-integrating-maximum-entropy-for","slug":"soft-qmix-integrating-maximum-entropy-for","title":"Soft-QMIX: Integrating Maximum Entropy For Monotonic Value Function Factorization","date":"2024-06-20","arxiv_id":"2406.13930","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-offline-reinforcement-learning-the","slug":"efficient-offline-reinforcement-learning-the","title":"Efficient Offline Reinforcement Learning: The Critic is Critical","date":"2024-06-19","arxiv_id":"2406.13376","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-minimal-reinforcement-learning","slug":"discovering-minimal-reinforcement-learning","title":"Discovering Minimal Reinforcement Learning Environments","date":"2024-06-18","arxiv_id":"2406.12589","repositories_listed":1,"syntology":null},{"url":"/paper/more-efficient-randomized-exploration-for","slug":"more-efficient-randomized-exploration-for","title":"More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling","date":"2024-06-18","arxiv_id":"2406.12241","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/more-efficient-randomized-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2406.12241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12241"}},"official":{"repos":["panxulab/lsvi-ase"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/is-poisoning-a-real-threat-to-llm-alignment","slug":"is-poisoning-a-real-threat-to-llm-alignment","title":"Is poisoning a real threat to LLM alignment? Maybe more so than you think","date":"2024-06-17","arxiv_id":"2406.12091","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":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) · 1 unverified","sample_list":"/paper/is-poisoning-a-real-threat-to-llm-alignment#ran","syntology_url":"https://syntology.ai/paper/2406.12091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12091"}},"official":{"repos":["pankayaraj/RLHFPoisoning"],"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/toward-optimal-llm-alignments-using-two","slug":"toward-optimal-llm-alignments-using-two","title":"Toward Optimal LLM Alignments Using Two-Player Games","date":"2024-06-16","arxiv_id":"2406.10977","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/toward-optimal-llm-alignments-using-two#ran","syntology_url":"https://syntology.ai/paper/2406.10977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10977"}},"official":{"repos":["ruizheng20/gpo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-model-based-reinforcement-learning-1","slug":"robust-model-based-reinforcement-learning-1","title":"Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model","date":"2024-06-14","arxiv_id":"2406.09976","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-model-based-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2406.09976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09976"}},"official":{"repos":["rmbpo-eval/rmbpo-eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-reinforcement-learning-for-swarm","slug":"hierarchical-reinforcement-learning-for-swarm","title":"Hierarchical Reinforcement Learning for Swarm Confrontation with High Uncertainty","date":"2024-06-12","arxiv_id":"2406.07877","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-to-disentangle","slug":"reinforcement-learning-to-disentangle","title":"Reinforcement Learning to Disentangle Multiqubit Quantum States from Partial Observations","date":"2024-06-12","arxiv_id":"2406.07884","repositories_listed":1,"syntology":null},{"url":"/paper/rrls-robust-reinforcement-learning-suite","slug":"rrls-robust-reinforcement-learning-suite","title":"RRLS : Robust Reinforcement Learning Suite","date":"2024-06-12","arxiv_id":"2406.08406","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/rrls-robust-reinforcement-learning-suite#ran","syntology_url":"https://syntology.ai/paper/2406.08406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08406"}},"official":{"repos":["sureli/rrls"],"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/the-max-min-formulation-of-multi-objective","slug":"the-max-min-formulation-of-multi-objective","title":"The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm","date":"2024-06-12","arxiv_id":"2406.07826","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/the-max-min-formulation-of-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2406.07826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07826"}},"official":{"repos":["giseung-park/maxmin-morl"],"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/multi-objective-reinforcement-learning-from","slug":"multi-objective-reinforcement-learning-from","title":"Multi-objective Reinforcement learning from AI Feedback","date":"2024-06-11","arxiv_id":"2406.07295","repositories_listed":1,"syntology":null},{"url":"/paper/pufferlib-making-reinforcement-learning","slug":"pufferlib-making-reinforcement-learning","title":"PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice","date":"2024-06-11","arxiv_id":"2406.12905","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-aware-spectrum-sharing-in-internet","slug":"semantic-aware-spectrum-sharing-in-internet","title":"Semantic-Aware Spectrum Sharing in Internet of Vehicles Based on Deep Reinforcement Learning","date":"2024-06-11","arxiv_id":"2406.07213","repositories_listed":1,"syntology":null},{"url":"/paper/coprocessor-actor-critic-a-model-based","slug":"coprocessor-actor-critic-a-model-based","title":"Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation","date":"2024-06-10","arxiv_id":"2406.06714","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/coprocessor-actor-critic-a-model-based#ran","syntology_url":"https://syntology.ai/paper/2406.06714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06714"}},"official":{"repos":["michelllepan/neural-coprocessors"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-multi-objective-reinforcement-learning","slug":"deep-multi-objective-reinforcement-learning","title":"Deep Multi-Objective Reinforcement Learning for Utility-Based Infrastructural Maintenance Optimization","date":"2024-06-10","arxiv_id":"2406.06184","repositories_listed":1,"syntology":null},{"url":"/paper/towards-real-world-efficiency-domain","slug":"towards-real-world-efficiency-domain","title":"Towards Real-World Efficiency: Domain Randomization in Reinforcement Learning for Pre-Capture of Free-Floating Moving Targets by Autonomous Robots","date":"2024-06-10","arxiv_id":"2406.06460","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-perspectives-on-error","slug":"probabilistic-perspectives-on-error","title":"Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning","date":"2024-06-07","arxiv_id":"2406.04724","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/probabilistic-perspectives-on-error#ran","syntology_url":"https://syntology.ai/paper/2406.04724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04724"}},"official":{"repos":["romanbelaire/acoe-robust-rl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/reinforcement-learning-and-regret-bounds-for","slug":"reinforcement-learning-and-regret-bounds-for","title":"Reinforcement Learning and Regret Bounds for Admission Control","date":"2024-06-07","arxiv_id":"2406.04766","repositories_listed":1,"syntology":null},{"url":"/paper/skill-aware-mutual-information-optimisation","slug":"skill-aware-mutual-information-optimisation","title":"Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning","date":"2024-06-07","arxiv_id":"2406.04815","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":1,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/skill-aware-mutual-information-optimisation#ran","syntology_url":"https://syntology.ai/paper/2406.04815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04815"}},"official":{"repos":["uoe-agents/sami"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stabilizing-extreme-q-learning-by-maclaurin","slug":"stabilizing-extreme-q-learning-by-maclaurin","title":"Stabilizing Extreme Q-learning by Maclaurin Expansion","date":"2024-06-07","arxiv_id":"2406.04896","repositories_listed":1,"syntology":null},{"url":"/paper/deterministic-uncertainty-propagation-for","slug":"deterministic-uncertainty-propagation-for","title":"Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.04088","repositories_listed":1,"syntology":null},{"url":"/paper/hackatari-atari-learning-environments-for","slug":"hackatari-atari-learning-environments-for","title":"HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.03997","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/hackatari-atari-learning-environments-for#ran","syntology_url":"https://syntology.ai/paper/2406.03997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03997"}},"official":{"repos":["k4ntz/HackAtari"],"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/reflective-policy-optimization","slug":"reflective-policy-optimization","title":"Reflective Policy Optimization","date":"2024-06-06","arxiv_id":"2406.03678","repositories_listed":1,"syntology":null},{"url":"/paper/spatio-temporal-early-prediction-based-on","slug":"spatio-temporal-early-prediction-based-on","title":"STEMO: Early Spatio-temporal Forecasting with Multi-Objective Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.04035","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/spatio-temporal-early-prediction-based-on#ran","syntology_url":"https://syntology.ai/paper/2406.04035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04035"}},"official":{"repos":["coco0106/MO-STEP"],"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/commonpower-supercharging-machine-learning","slug":"commonpower-supercharging-machine-learning","title":"CommonPower: A Framework for Safe Data-Driven Smart Grid Control","date":"2024-06-05","arxiv_id":"2406.03231","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-scalable-hessian-diagonal","slug":"revisiting-scalable-hessian-diagonal","title":"Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning","date":"2024-06-05","arxiv_id":"2406.03276","repositories_listed":1,"syntology":null},{"url":"/paper/moseac-streamlined-variable-time-step","slug":"moseac-streamlined-variable-time-step","title":"MOSEAC: Streamlined Variable Time Step Reinforcement Learning","date":"2024-06-03","arxiv_id":"2406.01521","repositories_listed":1,"syntology":null},{"url":"/paper/reciprocal-reward-influence-encourages","slug":"reciprocal-reward-influence-encourages","title":"Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents","date":"2024-06-03","arxiv_id":"2406.01641","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/reciprocal-reward-influence-encourages#ran","syntology_url":"https://syntology.ai/paper/2406.01641","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01641"}},"official":{"repos":["johnlyzhou/reciprocator"],"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/stochastic-bilevel-optimization-with-lower","slug":"stochastic-bilevel-optimization-with-lower","title":"Contextual Bilevel Reinforcement Learning for Incentive Alignment","date":"2024-06-03","arxiv_id":"2406.01575","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/stochastic-bilevel-optimization-with-lower#ran","syntology_url":"https://syntology.ai/paper/2406.01575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01575"}},"official":{"repos":["lasgroup/hpgd"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/furl-visual-language-models-as-fuzzy-rewards","slug":"furl-visual-language-models-as-fuzzy-rewards","title":"FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning","date":"2024-06-02","arxiv_id":"2406.00645","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/furl-visual-language-models-as-fuzzy-rewards#ran","syntology_url":"https://syntology.ai/paper/2406.00645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00645"}},"official":{"repos":["fuyw/furl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/artificial-generational-intelligence-cultural","slug":"artificial-generational-intelligence-cultural","title":"Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning","date":"2024-06-01","arxiv_id":"2406.00392","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":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/artificial-generational-intelligence-cultural#ran","syntology_url":"https://syntology.ai/paper/2406.00392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00392"}},"official":{"repos":["flairox/cultural-accumulation"],"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","unlocated"]}}},{"url":"/paper/amortizing-intractable-inference-in-diffusion","slug":"amortizing-intractable-inference-in-diffusion","title":"Amortizing intractable inference in diffusion models for vision, language, and control","date":"2024-05-31","arxiv_id":"2405.20971","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/amortizing-intractable-inference-in-diffusion#ran","syntology_url":"https://syntology.ai/paper/2405.20971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20971"}},"official":{"repos":["gfnorg/diffusion-finetuning"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bayesian-design-principles-for-offline-to","slug":"bayesian-design-principles-for-offline-to","title":"Bayesian Design Principles for Offline-to-Online Reinforcement Learning","date":"2024-05-31","arxiv_id":"2405.20984","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/bayesian-design-principles-for-offline-to#ran","syntology_url":"https://syntology.ai/paper/2405.20984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20984"}},"official":{"repos":["YiqinYang/BOORL"],"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/enhancing-efficiency-of-safe-reinforcement","slug":"enhancing-efficiency-of-safe-reinforcement","title":"Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation","date":"2024-05-31","arxiv_id":"2405.20860","repositories_listed":1,"syntology":null},{"url":"/paper/in-context-decision-transformer-reinforcement","slug":"in-context-decision-transformer-reinforcement","title":"In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought","date":"2024-05-31","arxiv_id":"2405.20692","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/in-context-decision-transformer-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2405.20692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20692"}},"official":{"repos":["silihuang-ai/idt"],"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","unlocated"]}}},{"url":"/paper/opentensor-reproducing-faster-matrix","slug":"opentensor-reproducing-faster-matrix","title":"OpenTensor: Reproducing Faster Matrix Multiplication Discovering Algorithms","date":"2024-05-31","arxiv_id":"2405.20748","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-advantage-guided-policy","slug":"adaptive-advantage-guided-policy","title":"Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning","date":"2024-05-30","arxiv_id":"2405.19909","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/adaptive-advantage-guided-policy#ran","syntology_url":"https://syntology.ai/paper/2405.19909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19909"}},"official":{"repos":["ltlhuuu/a2pr"],"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/aquatic-navigation-a-challenging-benchmark","slug":"aquatic-navigation-a-challenging-benchmark","title":"Aquatic Navigation: A Challenging Benchmark for Deep Reinforcement Learning","date":"2024-05-30","arxiv_id":"2405.20534","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-policies-creating-a-trust-region","slug":"diffusion-policies-creating-a-trust-region","title":"Diffusion Policies creating a Trust Region for Offline Reinforcement Learning","date":"2024-05-30","arxiv_id":"2405.19690","repositories_listed":1,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":20,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diffusion-policies-creating-a-trust-region#ran","syntology_url":"https://syntology.ai/paper/2405.19690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19690"}},"official":{"repos":["tianyucodings/diffusion_trusted_q_learning"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-reinforcement-learning-with-label","slug":"enhancing-reinforcement-learning-with-label","title":"Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding","date":"2024-05-30","arxiv_id":"2405.19763","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-based-dynamics-models-for-long","slug":"diffusion-based-dynamics-models-for-long","title":"Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning","date":"2024-05-29","arxiv_id":"2405.19189","repositories_listed":1,"syntology":null},{"url":"/paper/rlexplore-accelerating-research-in","slug":"rlexplore-accelerating-research-in","title":"RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning","date":"2024-05-29","arxiv_id":"2405.19548","repositories_listed":1,"syntology":null},{"url":"/paper/statistical-context-detection-for-deep","slug":"statistical-context-detection-for-deep","title":"Statistical Context Detection for Deep Lifelong Reinforcement Learning","date":"2024-05-29","arxiv_id":"2405.19047","repositories_listed":1,"syntology":null},{"url":"/paper/an-approach-to-improve-agent-learning-via","slug":"an-approach-to-improve-agent-learning-via","title":"An agent design with goal reaching guarantees for enhancement of learning","date":"2024-05-28","arxiv_id":"2405.18118","repositories_listed":1,"syntology":null},{"url":"/paper/getting-more-juice-out-of-the-sft-data-reward","slug":"getting-more-juice-out-of-the-sft-data-reward","title":"Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment","date":"2024-05-28","arxiv_id":"2405.17888","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/getting-more-juice-out-of-the-sft-data-reward#ran","syntology_url":"https://syntology.ai/paper/2405.17888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17888"}},"official":{"repos":["jasonjiaxiangli/reward_learning_sft"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/harmodt-harmony-multi-task-decision","slug":"harmodt-harmony-multi-task-decision","title":"HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning","date":"2024-05-28","arxiv_id":"2405.18080","repositories_listed":1,"syntology":null},{"url":"/paper/pytag-tabletop-games-for-multi-agent","slug":"pytag-tabletop-games-for-multi-agent","title":"PyTAG: Tabletop Games for Multi-Agent Reinforcement Learning","date":"2024-05-28","arxiv_id":"2405.18123","repositories_listed":1,"syntology":null},{"url":"/paper/reinforced-model-predictive-control-via-trust","slug":"reinforced-model-predictive-control-via-trust","title":"Reinforced Model Predictive Control via Trust-Region Quasi-Newton Policy Optimization","date":"2024-05-28","arxiv_id":"2405.17983","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-in-dynamic-treatment","slug":"reinforcement-learning-in-dynamic-treatment","title":"Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination","date":"2024-05-28","arxiv_id":"2405.18556","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_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","sample_list":"/paper/reinforcement-learning-in-dynamic-treatment#ran","syntology_url":"https://syntology.ai/paper/2405.18556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18556"}},"official":{"repos":["gilesluo/reassessdtr"],"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"]}}},{"url":"/paper/safe-reinforcement-learning-in-black-box","slug":"safe-reinforcement-learning-in-black-box","title":"Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding","date":"2024-05-28","arxiv_id":"2405.18180","repositories_listed":1,"syntology":null},{"url":"/paper/a-recipe-for-unbounded-data-augmentation-in","slug":"a-recipe-for-unbounded-data-augmentation-in","title":"A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning","date":"2024-05-27","arxiv_id":"2405.17416","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-recipe-for-unbounded-data-augmentation-in#ran","syntology_url":"https://syntology.ai/paper/2405.17416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17416"}},"official":{"repos":["aalmuzairee/dmcgb2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/gta-generative-trajectory-augmentation-with","slug":"gta-generative-trajectory-augmentation-with","title":"GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning","date":"2024-05-27","arxiv_id":"2405.16907","repositories_listed":1,"syntology":{"n":37,"n_ran":34,"n_constructed":0,"n_ran_checked":29,"n_instrument":5,"n_unverified":3,"n_honours":3,"n_violates":4,"n_no_contract":22,"n_pointer_only":5,"phrase":"34 ran (of which 0 constructed an object rather than computing a result; 29 with no instrument failure: 3 honoured, 4 violated, 22 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/gta-generative-trajectory-augmentation-with#ran","syntology_url":"https://syntology.ai/paper/2405.16907","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16907"}},"official":{"repos":["jaewoopudding/gta"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/surprise-adaptive-intrinsic-motivation-for","slug":"surprise-adaptive-intrinsic-motivation-for","title":"Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning","date":"2024-05-27","arxiv_id":"2405.17243","repositories_listed":1,"syntology":null},{"url":"/paper/symmetric-reinforcement-learning-loss-for","slug":"symmetric-reinforcement-learning-loss-for","title":"Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales","date":"2024-05-27","arxiv_id":"2405.17618","repositories_listed":1,"syntology":null},{"url":"/paper/multi-state-td-target-for-model-free","slug":"multi-state-td-target-for-model-free","title":"Multi-State TD Target for Model-Free Reinforcement Learning","date":"2024-05-26","arxiv_id":"2405.16522","repositories_listed":1,"syntology":null},{"url":"/paper/safe-and-balanced-a-framework-for-constrained","slug":"safe-and-balanced-a-framework-for-constrained","title":"Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning","date":"2024-05-26","arxiv_id":"2405.16390","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-and-balanced-a-framework-for-constrained#ran","syntology_url":"https://syntology.ai/paper/2405.16390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16390"}},"official":{"repos":["SafeRL-Lab/Safe-Multi-Objective-MuJoCo"],"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/deep-reinforcement-learning-with-enhanced-ppo","slug":"deep-reinforcement-learning-with-enhanced-ppo","title":"Deep Reinforcement Learning with Enhanced PPO for Safe Mobile Robot Navigation","date":"2024-05-25","arxiv_id":"2405.16266","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-based-reinforcement-learning-via-q","slug":"diffusion-based-reinforcement-learning-via-q","title":"Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization","date":"2024-05-25","arxiv_id":"2405.16173","repositories_listed":1,"syntology":null},{"url":"/paper/pausing-policy-learning-in-non-stationary","slug":"pausing-policy-learning-in-non-stationary","title":"Pausing Policy Learning in Non-stationary Reinforcement Learning","date":"2024-05-25","arxiv_id":"2405.16053","repositories_listed":1,"syntology":null},{"url":"/paper/safe-deep-model-based-reinforcement-learning","slug":"safe-deep-model-based-reinforcement-learning","title":"Safe Deep Model-Based Reinforcement Learning with Lyapunov Functions","date":"2024-05-25","arxiv_id":"2405.16184","repositories_listed":1,"syntology":null},{"url":"/paper/verified-safe-reinforcement-learning-for","slug":"verified-safe-reinforcement-learning-for","title":"Verified Safe Reinforcement Learning for Neural Network Dynamic Models","date":"2024-05-25","arxiv_id":"2405.15994","repositories_listed":1,"syntology":null},{"url":"/paper/ivideogpt-interactive-videogpts-are-scalable","slug":"ivideogpt-interactive-videogpts-are-scalable","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","date":"2024-05-24","arxiv_id":"2405.15223","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 2 unverified","sample_list":"/paper/ivideogpt-interactive-videogpts-are-scalable#ran","syntology_url":"https://syntology.ai/paper/2405.15223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15223"}},"official":{"repos":["thuml/iVideoGPT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-structure-aware-framework-for-learning","slug":"a-structure-aware-framework-for-learning","title":"A Structure-Aware Framework for Learning Device Placements on Computation Graphs","date":"2024-05-23","arxiv_id":"2405.14185","repositories_listed":1,"syntology":null},{"url":"/paper/agile-a-novel-framework-of-llm-agents","slug":"agile-a-novel-framework-of-llm-agents","title":"AGILE: A Novel Reinforcement Learning Framework of LLM Agents","date":"2024-05-23","arxiv_id":"2405.14751","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/agile-a-novel-framework-of-llm-agents#ran","syntology_url":"https://syntology.ai/paper/2405.14751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14751"}},"official":{"repos":["bytarnish/agile"],"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/controlling-behavioral-diversity-in-multi","slug":"controlling-behavioral-diversity-in-multi","title":"Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning","date":"2024-05-23","arxiv_id":"2405.15054","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/controlling-behavioral-diversity-in-multi#ran","syntology_url":"https://syntology.ai/paper/2405.15054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15054"}},"official":{"repos":["proroklab/controllingbehavioraldiversity"],"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/interpretable-and-editable-programmatic-tree","slug":"interpretable-and-editable-programmatic-tree","title":"Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning","date":"2024-05-23","arxiv_id":"2405.14956","repositories_listed":1,"syntology":null},{"url":"/paper/multi-turn-reinforcement-learning-from","slug":"multi-turn-reinforcement-learning-from","title":"Multi-turn Reinforcement Learning from Preference Human Feedback","date":"2024-05-23","arxiv_id":"2405.14655","repositories_listed":1,"syntology":null},{"url":"/paper/offline-reinforcement-learning-from-datasets","slug":"offline-reinforcement-learning-from-datasets","title":"Offline Reinforcement Learning from Datasets with Structured Non-Stationarity","date":"2024-05-23","arxiv_id":"2405.14114","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":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) · 2 unverified","sample_list":"/paper/offline-reinforcement-learning-from-datasets#ran","syntology_url":"https://syntology.ai/paper/2405.14114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14114"}},"official":{"repos":["johannesack/offlinerlstructurednonstationarity"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/peac-unsupervised-pre-training-for-cross","slug":"peac-unsupervised-pre-training-for-cross","title":"PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning","date":"2024-05-23","arxiv_id":"2405.14073","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/peac-unsupervised-pre-training-for-cross#ran","syntology_url":"https://syntology.ai/paper/2405.14073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14073"}},"official":{"repos":["thu-ml/CEURL"],"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/formally-verifying-deep-reinforcement","slug":"formally-verifying-deep-reinforcement","title":"Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificates","date":"2024-05-22","arxiv_id":"2405.14058","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/formally-verifying-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2405.14058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14058"}},"official":{"repos":["neuralnetworkverification/artifact-fmcad24-docking"],"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/knowledge-graph-reasoning-with-self","slug":"knowledge-graph-reasoning-with-self","title":"Knowledge Graph Reasoning with Self-supervised Reinforcement Learning","date":"2024-05-22","arxiv_id":"2405.13640","repositories_listed":1,"syntology":null},{"url":"/paper/lusifer-llm-based-user-simulated-feedback","slug":"lusifer-llm-based-user-simulated-feedback","title":"Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems","date":"2024-05-22","arxiv_id":"2405.13362","repositories_listed":1,"syntology":null},{"url":"/paper/maximum-entropy-reinforcement-learning-via","slug":"maximum-entropy-reinforcement-learning-via","title":"Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow","date":"2024-05-22","arxiv_id":"2405.13629","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-for-adaptive-mcmc","slug":"reinforcement-learning-for-adaptive-mcmc","title":"Reinforcement Learning for Adaptive MCMC","date":"2024-05-22","arxiv_id":"2405.13574","repositories_listed":1,"syntology":null},{"url":"/paper/tackling-decision-processes-with-non","slug":"tackling-decision-processes-with-non","title":"Tackling Decision Processes with Non-Cumulative Objectives using Reinforcement Learning","date":"2024-05-22","arxiv_id":"2405.13609","repositories_listed":1,"syntology":null}],"record_sha256":"b971e722b248669b4a5ce30d9847ede432e898f84685bc33ef0040d71dab2176","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}