{"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/29","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":29,"pages_in_order":135,"rows_per_page":100,"rows":[2801,2900],"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/28","next":"/task/reinforcement-learning-2/papers/30","papers":[{"url":"/paper/aligning-an-optical-interferometer-with-beam","slug":"aligning-an-optical-interferometer-with-beam","title":"Aligning an optical interferometer with beam divergence control and continuous action space","date":"2021-07-09","arxiv_id":"2107.04457","repositories_listed":1,"syntology":null},{"url":"/paper/offline-meta-reinforcement-learning-with-1","slug":"offline-meta-reinforcement-learning-with-1","title":"Offline Meta-Reinforcement Learning with Online Self-Supervision","date":"2021-07-08","arxiv_id":"2107.03974","repositories_listed":1,"syntology":null},{"url":"/paper/distributed-online-service-coordination-using","slug":"distributed-online-service-coordination-using","title":"Distributed Online Service Coordination Using Deep Reinforcement Learning","date":"2021-07-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/adarl-what-where-and-how-to-adapt-in-transfer","slug":"adarl-what-where-and-how-to-adapt-in-transfer","title":"AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning","date":"2021-07-06","arxiv_id":"2107.02729","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/adarl-what-where-and-how-to-adapt-in-transfer#ran","syntology_url":"https://syntology.ai/paper/2107.02729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02729"}},"official":{"repos":["adaptive-rl/adarl-code"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-modal-mutual-information-mummi-training","slug":"multi-modal-mutual-information-mummi-training","title":"Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning","date":"2021-07-06","arxiv_id":"2107.02339","repositories_listed":1,"syntology":null},{"url":"/paper/the-sjtu-system-for-dcase2021-challenge-task","slug":"the-sjtu-system-for-dcase2021-challenge-task","title":"THE SJTU SYSTEM FOR DCASE2021 CHALLENGE TASK 6: AUDIO CAPTIONING BASED ON ENCODER PRE-TRAINING AND REINFORCEMENT LEARNING","date":"2021-07-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/agents-that-listen-high-throughput","slug":"agents-that-listen-high-throughput","title":"Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems","date":"2021-07-05","arxiv_id":"2107.02195","repositories_listed":1,"syntology":null},{"url":"/paper/ensemble-and-auxiliary-tasks-for-data","slug":"ensemble-and-auxiliary-tasks-for-data","title":"Ensemble and Auxiliary Tasks for Data-Efficient Deep Reinforcement Learning","date":"2021-07-05","arxiv_id":"2107.01904","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ensemble-and-auxiliary-tasks-for-data#ran","syntology_url":"https://syntology.ai/paper/2107.01904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.01904"}},"official":{"repos":["NUS-LID/RENAULT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-efficient-reinforcement-learning-via-2","slug":"sample-efficient-reinforcement-learning-via-2","title":"Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation","date":"2021-07-05","arxiv_id":"2107.01825","repositories_listed":1,"syntology":null},{"url":"/paper/mava-a-research-framework-for-distributed","slug":"mava-a-research-framework-for-distributed","title":"Mava: a research library for distributed multi-agent reinforcement learning in JAX","date":"2021-07-03","arxiv_id":"2107.01460","repositories_listed":1,"syntology":null},{"url":"/paper/where-is-the-grass-greener-revisiting","slug":"where-is-the-grass-greener-revisiting","title":"Optimality Inductive Biases and Agnostic Guidelines for Offline Reinforcement Learning","date":"2021-07-03","arxiv_id":"2107.01407","repositories_listed":1,"syntology":null},{"url":"/paper/ensemble-kalman-filter-enkf-for-reinforcement","slug":"ensemble-kalman-filter-enkf-for-reinforcement","title":"Controlled Interacting Particle Algorithms for Simulation-based Reinforcement Learning","date":"2021-07-02","arxiv_id":"2107.01244","repositories_listed":1,"syntology":null},{"url":"/paper/rl-ncs-reinforcement-learning-based-data","slug":"rl-ncs-reinforcement-learning-based-data","title":"RL-NCS: Reinforcement learning based data-driven approach for nonuniform compressed sensing","date":"2021-07-02","arxiv_id":"2107.00838","repositories_listed":1,"syntology":null},{"url":"/paper/systematic-evaluation-of-causal-discovery-in-1","slug":"systematic-evaluation-of-causal-discovery-in-1","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","date":"2021-07-02","arxiv_id":"2107.00848","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/systematic-evaluation-of-causal-discovery-in-1#ran","syntology_url":"https://syntology.ai/paper/2107.00848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00848"}},"official":{"repos":["dido1998/CausalMBRL"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/distilling-reinforcement-learning-tricks-for","slug":"distilling-reinforcement-learning-tricks-for","title":"Distilling Reinforcement Learning Tricks for Video Games","date":"2021-07-01","arxiv_id":"2107.00703","repositories_listed":1,"syntology":null},{"url":"/paper/offline-to-online-reinforcement-learning-via","slug":"offline-to-online-reinforcement-learning-via","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","date":"2021-07-01","arxiv_id":"2107.00591","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-for-abstractive","slug":"reinforcement-learning-for-abstractive","title":"Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards","date":"2021-07-01","arxiv_id":"2107.00176","repositories_listed":1,"syntology":null},{"url":"/paper/experience-driven-pcg-via-reinforcement","slug":"experience-driven-pcg-via-reinforcement","title":"Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros Study","date":"2021-06-30","arxiv_id":"2106.15877","repositories_listed":1,"syntology":null},{"url":"/paper/koopman-spectrum-nonlinear-regulator-and","slug":"koopman-spectrum-nonlinear-regulator-and","title":"Koopman Spectrum Nonlinear Regulators and Efficient Online Learning","date":"2021-06-30","arxiv_id":"2106.15775","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-adversarial-attacks-on-1","slug":"understanding-adversarial-attacks-on-1","title":"Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning","date":"2021-06-30","arxiv_id":"2106.15860","repositories_listed":1,"syntology":null},{"url":"/paper/a-convergent-and-efficient-deep-q-network","slug":"a-convergent-and-efficient-deep-q-network","title":"Convergent and Efficient Deep Q Network Algorithm","date":"2021-06-29","arxiv_id":"2106.15419","repositories_listed":1,"syntology":null},{"url":"/paper/analysis-and-control-of-a-planar-quadrotor","slug":"analysis-and-control-of-a-planar-quadrotor","title":"Analysis and Control of a Planar Quadrotor","date":"2021-06-29","arxiv_id":"2106.15134","repositories_listed":1,"syntology":null},{"url":"/paper/globally-optimal-hierarchical-reinforcement","slug":"globally-optimal-hierarchical-reinforcement","title":"Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes","date":"2021-06-29","arxiv_id":"2106.15380","repositories_listed":1,"syntology":null},{"url":"/paper/learning-task-informed-abstraction","slug":"learning-task-informed-abstraction","title":"Learning Task Informed Abstractions","date":"2021-06-29","arxiv_id":"2106.15612","repositories_listed":1,"syntology":null},{"url":"/paper/causal-reinforcement-learning-using","slug":"causal-reinforcement-learning-using","title":"Causal Reinforcement Learning using Observational and Interventional Data","date":"2021-06-28","arxiv_id":"2106.14421","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-curriculum-learning-in-a-complex","slug":"multi-task-curriculum-learning-in-a-complex","title":"Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft","date":"2021-06-28","arxiv_id":"2106.14876","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-task-curriculum-learning-in-a-complex#ran","syntology_url":"https://syntology.ai/paper/2106.14876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14876"}},"official":null}},{"url":"/paper/graph-convolutional-memory-for-deep","slug":"graph-convolutional-memory-for-deep","title":"Graph Convolutional Memory using Topological Priors","date":"2021-06-27","arxiv_id":"2106.14117","repositories_listed":1,"syntology":null},{"url":"/paper/autopipeline-synthesize-data-pipelines-by","slug":"autopipeline-synthesize-data-pipelines-by","title":"Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Search","date":"2021-06-25","arxiv_id":"2106.13861","repositories_listed":1,"syntology":null},{"url":"/paper/compositional-reinforcement-learning-from","slug":"compositional-reinforcement-learning-from","title":"Compositional Reinforcement Learning from Logical Specifications","date":"2021-06-25","arxiv_id":"2106.13906","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/compositional-reinforcement-learning-from#ran","syntology_url":"https://syntology.ai/paper/2106.13906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13906"}},"official":{"repos":["keyshor/dirl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-goal-reinforcement-learning","slug":"multi-goal-reinforcement-learning","title":"Multi-Goal Reinforcement Learning environments for simulated Franka Emika Panda robot","date":"2021-06-25","arxiv_id":"2106.13687","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-goal-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2106.13687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13687"}},"official":{"repos":["qgallouedec/panda-gym"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/brax-a-differentiable-physics-engine-for","slug":"brax-a-differentiable-physics-engine-for","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","date":"2021-06-24","arxiv_id":"2106.13281","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/brax-a-differentiable-physics-engine-for#ran","syntology_url":"https://syntology.ai/paper/2106.13281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13281"}},"official":{"repos":["google/brax"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/model-based-reinforcement-learning-via-latent-1","slug":"model-based-reinforcement-learning-via-latent-1","title":"Model-Based Reinforcement Learning via Latent-Space Collocation","date":"2021-06-24","arxiv_id":"2106.13229","repositories_listed":1,"syntology":null},{"url":"/paper/unifying-gradient-estimators-for-meta","slug":"unifying-gradient-estimators-for-meta","title":"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation","date":"2021-06-24","arxiv_id":"2106.13125","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unifying-gradient-estimators-for-meta#ran","syntology_url":"https://syntology.ai/paper/2106.13125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13125"}},"official":{"repos":["robintyh1/neurips2021-meta-gradient-offpolicy-evaluation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bregman-gradient-policy-optimization","slug":"bregman-gradient-policy-optimization","title":"Bregman Gradient Policy Optimization","date":"2021-06-23","arxiv_id":"2106.12112","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bregman-gradient-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/2106.12112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12112"}},"official":{"repos":["gaosh/bgpo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-based-dialogue-guided","slug":"reinforcement-learning-based-dialogue-guided","title":"Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations","date":"2021-06-23","arxiv_id":"2106.12384","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-for-phy-layer","slug":"reinforcement-learning-for-phy-layer","title":"Reinforcement Learning for Physical Layer Communications","date":"2021-06-22","arxiv_id":"2106.11595","repositories_listed":1,"syntology":null},{"url":"/paper/a-max-min-entropy-framework-for-reinforcement","slug":"a-max-min-entropy-framework-for-reinforcement","title":"A Max-Min Entropy Framework for Reinforcement Learning","date":"2021-06-19","arxiv_id":"2106.10517","repositories_listed":1,"syntology":null},{"url":"/paper/towards-safe-reinforcement-learning-via-1","slug":"towards-safe-reinforcement-learning-via-1","title":"Towards Safe Reinforcement Learning via Constraining Conditional Value at Risk","date":"2021-06-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/real-time-attacks-against-deep-reinforcement","slug":"real-time-attacks-against-deep-reinforcement","title":"Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses","date":"2021-06-16","arxiv_id":"2106.08746","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/real-time-attacks-against-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2106.08746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08746"}},"official":{"repos":["ssg-research/ad3-action-distribution-divergence-detector"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-the-weaknesses-of-reinforcement-1","slug":"revisiting-the-weaknesses-of-reinforcement-1","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","date":"2021-06-16","arxiv_id":"2106.08942","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/revisiting-the-weaknesses-of-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2106.08942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08942"}},"official":{"repos":["samuki/reinforce-joey"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-reinforcement-learning-using-advantage","slug":"safe-reinforcement-learning-using-advantage","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","date":"2021-06-16","arxiv_id":"2106.09110","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":6,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-reinforcement-learning-using-advantage#ran","syntology_url":"https://syntology.ai/paper/2106.09110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09110"}},"official":{"repos":["nolanwagener/safe_rl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-reinforcement-learning-for-conservation","slug":"deep-reinforcement-learning-for-conservation","title":"Deep Reinforcement Learning for Conservation Decisions","date":"2021-06-15","arxiv_id":"2106.08272","repositories_listed":1,"syntology":null},{"url":"/paper/randomized-exploration-for-reinforcement","slug":"randomized-exploration-for-reinforcement","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","date":"2021-06-15","arxiv_id":"2106.07841","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/randomized-exploration-for-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2106.07841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07841"}},"official":{"repos":["qlan3/Explorer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-reinforcement-learning-under-minimax","slug":"robust-reinforcement-learning-under-minimax","title":"Robust Reinforcement Learning Under Minimax Regret for Green Security","date":"2021-06-15","arxiv_id":"2106.08413","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-reinforcement-learning-under-minimax#ran","syntology_url":"https://syntology.ai/paper/2106.08413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08413"}},"official":{"repos":["lily-x/mirror"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rsoccer-a-framework-for-studying","slug":"rsoccer-a-framework-for-studying","title":"rSoccer: A Framework for Studying Reinforcement Learning in Small and Very Small Size Robot Soccer","date":"2021-06-15","arxiv_id":"2106.12895","repositories_listed":1,"syntology":null},{"url":"/paper/learning-intrusion-prevention-policies","slug":"learning-intrusion-prevention-policies","title":"Learning Intrusion Prevention Policies through Optimal Stopping","date":"2021-06-14","arxiv_id":"2106.07160","repositories_listed":1,"syntology":null},{"url":"/paper/contingency-aware-influence-maximization-a","slug":"contingency-aware-influence-maximization-a","title":"Contingency-Aware Influence Maximization: A Reinforcement Learning Approach","date":"2021-06-13","arxiv_id":"2106.07039","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-based-group","slug":"deep-reinforcement-learning-based-group","title":"Deep Reinforcement Learning based Group Recommender System","date":"2021-06-13","arxiv_id":"2106.06900","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-as-one-big-sequence-1","slug":"reinforcement-learning-as-one-big-sequence-1","title":"Reinforcement Learning as One Big Sequence Modeling Problem","date":"2021-06-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-deep-reinforcement-learning-approach-to-4","slug":"a-deep-reinforcement-learning-approach-to-4","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","date":"2021-06-12","arxiv_id":"2106.06854","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/a-deep-reinforcement-learning-approach-to-4#ran","syntology_url":"https://syntology.ai/paper/2106.06854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06854"}},"official":{"repos":["sfujim/SR-DICE"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-game-theoretic-approach-to-multi-agent","slug":"a-game-theoretic-approach-to-multi-agent","title":"A Game-Theoretic Approach to Multi-Agent Trust Region Optimization","date":"2021-06-12","arxiv_id":"2106.06828","repositories_listed":1,"syntology":null},{"url":"/paper/douzero-mastering-doudizhu-with-self-play","slug":"douzero-mastering-doudizhu-with-self-play","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","date":"2021-06-11","arxiv_id":"2106.06135","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/douzero-mastering-doudizhu-with-self-play#ran","syntology_url":"https://syntology.ai/paper/2106.06135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06135"}},"official":{"repos":["kwai/DouZero"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/wax-ml-a-python-library-for-machine-learning","slug":"wax-ml-a-python-library-for-machine-learning","title":"WAX-ML: A Python library for machine learning and feedback loops on streaming data","date":"2021-06-11","arxiv_id":"2106.06524","repositories_listed":1,"syntology":null},{"url":"/paper/simplifying-deep-reinforcement-learning-via","slug":"simplifying-deep-reinforcement-learning-via","title":"Simplifying Deep Reinforcement Learning via Self-Supervision","date":"2021-06-10","arxiv_id":"2106.05526","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simplifying-deep-reinforcement-learning-via#ran","syntology_url":"https://syntology.ai/paper/2106.05526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05526"}},"official":{"repos":["daochenzha/SSRL"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/synthesising-reinforcement-learning-policies","slug":"synthesising-reinforcement-learning-policies","title":"Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning","date":"2021-06-10","arxiv_id":"2106.06009","repositories_listed":1,"syntology":null},{"url":"/paper/pretrained-encoders-are-all-you-need","slug":"pretrained-encoders-are-all-you-need","title":"Pretrained Encoders are All You Need","date":"2021-06-09","arxiv_id":"2106.05139","repositories_listed":1,"syntology":null},{"url":"/paper/pretraining-representations-for-data","slug":"pretraining-representations-for-data","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","date":"2021-06-09","arxiv_id":"2106.04799","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pretraining-representations-for-data#ran","syntology_url":"https://syntology.ai/paper/2106.04799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04799"}},"official":{"repos":["mila-iqia/SGI"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/self-attention-recurrent-summarization","slug":"self-attention-recurrent-summarization","title":"Self-Attention Recurrent Summarization Network with Reinforcement Learning for Video Summarization Task","date":"2021-06-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/self-paced-context-evaluation-for-contextual","slug":"self-paced-context-evaluation-for-contextual","title":"Self-Paced Context Evaluation for Contextual Reinforcement Learning","date":"2021-06-09","arxiv_id":"2106.05110","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-sparse-training-for-deep","slug":"dynamic-sparse-training-for-deep","title":"Dynamic Sparse Training for Deep Reinforcement Learning","date":"2021-06-08","arxiv_id":"2106.04217","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dynamic-sparse-training-for-deep#ran","syntology_url":"https://syntology.ai/paper/2106.04217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04217"}},"official":{"repos":["GhadaSokar/Dynamic-Sparse-Training-for-Deep-Reinforcement-Learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-markov-state-abstractions-for-deep","slug":"learning-markov-state-abstractions-for-deep","title":"Learning Markov State Abstractions for Deep Reinforcement Learning","date":"2021-06-08","arxiv_id":"2106.04379","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-markov-state-abstractions-for-deep#ran","syntology_url":"https://syntology.ai/paper/2106.04379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04379"}},"official":{"repos":["camall3n/markov-state-abstractions"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/believe-what-you-see-implicit-constraint","slug":"believe-what-you-see-implicit-constraint","title":"Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning","date":"2021-06-07","arxiv_id":"2106.03400","repositories_listed":1,"syntology":null},{"url":"/paper/task-driven-semantic-coding-via-reinforcement","slug":"task-driven-semantic-coding-via-reinforcement","title":"Task-driven Semantic Coding via Reinforcement Learning","date":"2021-06-07","arxiv_id":"2106.03511","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/task-driven-semantic-coding-via-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2106.03511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03511"}},"official":{"repos":["USTC-IMCL/Task-driven-Semantic-Coding-via-RL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/verifiable-and-compositional-reinforcement","slug":"verifiable-and-compositional-reinforcement","title":"Verifiable and Compositional Reinforcement Learning Systems","date":"2021-06-07","arxiv_id":"2106.05864","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/verifiable-and-compositional-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2106.05864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05864"}},"official":{"repos":["cyrusneary/verifiable-compositional-rl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/xirl-cross-embodiment-inverse-reinforcement","slug":"xirl-cross-embodiment-inverse-reinforcement","title":"XIRL: Cross-embodiment Inverse Reinforcement Learning","date":"2021-06-07","arxiv_id":"2106.03911","repositories_listed":1,"syntology":null},{"url":"/paper/control-oriented-model-based-reinforcement","slug":"control-oriented-model-based-reinforcement","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","date":"2021-06-06","arxiv_id":"2106.03273","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/control-oriented-model-based-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2106.03273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03273"}},"official":{"repos":["evgenii-nikishin/omd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/distributional-reinforcement-learning-with-4","slug":"distributional-reinforcement-learning-with-4","title":"Distributional Reinforcement Learning with Unconstrained Monotonic Neural Networks","date":"2021-06-06","arxiv_id":"2106.03228","repositories_listed":1,"syntology":null},{"url":"/paper/schedulenet-learn-to-solve-multi-agent","slug":"schedulenet-learn-to-solve-multi-agent","title":"ScheduleNet: Learn to solve multi-agent scheduling problems with reinforcement learning","date":"2021-06-06","arxiv_id":"2106.03051","repositories_listed":1,"syntology":null},{"url":"/paper/malib-a-parallel-framework-for-population","slug":"malib-a-parallel-framework-for-population","title":"MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning","date":"2021-06-05","arxiv_id":"2106.07551","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/malib-a-parallel-framework-for-population#ran","syntology_url":"https://syntology.ai/paper/2106.07551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07551"}},"official":{"repos":["sjtu-marl/malib"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/same-state-different-task-continual","slug":"same-state-different-task-continual","title":"Same State, Different Task: Continual Reinforcement Learning without Interference","date":"2021-06-05","arxiv_id":"2106.02940","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/same-state-different-task-continual#ran","syntology_url":"https://syntology.ai/paper/2106.02940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02940"}},"official":{"repos":["skezle/owl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/model-agnostic-and-scalable-counterfactual","slug":"model-agnostic-and-scalable-counterfactual","title":"Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning","date":"2021-06-04","arxiv_id":"2106.02597","repositories_listed":1,"syntology":null},{"url":"/paper/online-reinforcement-learning-with-sparse","slug":"online-reinforcement-learning-with-sparse","title":"Online reinforcement learning with sparse rewards through an active inference capsule","date":"2021-06-04","arxiv_id":"2106.02390","repositories_listed":1,"syntology":null},{"url":"/paper/rl-darts-differentiable-architecture-search","slug":"rl-darts-differentiable-architecture-search","title":"Differentiable Architecture Search for Reinforcement Learning","date":"2021-06-04","arxiv_id":"2106.02229","repositories_listed":1,"syntology":null},{"url":"/paper/a-consciousness-inspired-planning-agent-for","slug":"a-consciousness-inspired-planning-agent-for","title":"A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning","date":"2021-06-03","arxiv_id":"2106.02097","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-consciousness-inspired-planning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2106.02097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02097"}},"official":{"repos":["mila-iqia/conscious-planning"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/lifetime-policy-reuse-and-the-importance-of","slug":"lifetime-policy-reuse-and-the-importance-of","title":"Lifetime policy reuse and the importance of task capacity","date":"2021-06-03","arxiv_id":"2106.01741","repositories_listed":1,"syntology":null},{"url":"/paper/optimization-based-algebraic-multigrid","slug":"optimization-based-algebraic-multigrid","title":"Optimization-Based Algebraic Multigrid Coarsening Using Reinforcement Learning","date":"2021-06-03","arxiv_id":"2106.01854","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/optimization-based-algebraic-multigrid#ran","syntology_url":"https://syntology.ai/paper/2106.01854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01854"}},"official":{"repos":["compdyn/rl_grid_coarsen"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-reinforcement-learning-in-quantitative","slug":"deep-reinforcement-learning-in-quantitative","title":"Deep Reinforcement Learning in Quantitative Algorithmic Trading: A Review","date":"2021-05-31","arxiv_id":"2106.00123","repositories_listed":1,"syntology":null},{"url":"/paper/q-attention-enabling-efficient-learning-for","slug":"q-attention-enabling-efficient-learning-for","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","date":"2021-05-31","arxiv_id":"2105.14829","repositories_listed":1,"syntology":null},{"url":"/paper/a-nearly-blackwell-optimal-policy-gradient","slug":"a-nearly-blackwell-optimal-policy-gradient","title":"A nearly Blackwell-optimal policy gradient method","date":"2021-05-28","arxiv_id":"2105.13609","repositories_listed":1,"syntology":null},{"url":"/paper/improving-generalization-in-meta-rl-with","slug":"improving-generalization-in-meta-rl-with","title":"Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture","date":"2021-05-28","arxiv_id":"2105.13524","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/improving-generalization-in-meta-rl-with#ran","syntology_url":"https://syntology.ai/paper/2105.13524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13524"}},"official":{"repos":["suyoung-lee/ldm"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/adversarial-intrinsic-motivation-for","slug":"adversarial-intrinsic-motivation-for","title":"Adversarial Intrinsic Motivation for Reinforcement Learning","date":"2021-05-27","arxiv_id":"2105.13345","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/adversarial-intrinsic-motivation-for#ran","syntology_url":"https://syntology.ai/paper/2105.13345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13345"}},"official":{"repos":["iDurugkar/adversarial-intrinsic-motivation"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/exploitation-vs-caution-risk-sensitive","slug":"exploitation-vs-caution-risk-sensitive","title":"An Offline Risk-aware Policy Selection Method for Bayesian Markov Decision Processes","date":"2021-05-27","arxiv_id":"2105.13431","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/exploitation-vs-caution-risk-sensitive#ran","syntology_url":"https://syntology.ai/paper/2105.13431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13431"}},"official":{"repos":["giorgioangel/evc"],"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/successive-convex-approximation-based-off","slug":"successive-convex-approximation-based-off","title":"Successive Convex Approximation Based Off-Policy Optimization for Constrained Reinforcement Learning","date":"2021-05-26","arxiv_id":"2105.12545","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparison-of-reward-functions-in-q","slug":"a-comparison-of-reward-functions-in-q","title":"A Comparison of Reward Functions in Q-Learning Applied to a Cart Position Problem","date":"2021-05-25","arxiv_id":"2105.11617","repositories_listed":1,"syntology":null},{"url":"/paper/robust-value-iteration-for-continuous-control","slug":"robust-value-iteration-for-continuous-control","title":"Robust Value Iteration for Continuous Control Tasks","date":"2021-05-25","arxiv_id":"2105.12189","repositories_listed":1,"syntology":null},{"url":"/paper/towards-scalable-verification-of-rl-driven","slug":"towards-scalable-verification-of-rl-driven","title":"Towards Scalable Verification of Deep Reinforcement Learning","date":"2021-05-25","arxiv_id":"2105.11931","repositories_listed":1,"syntology":null},{"url":"/paper/an-efficient-application-of-neuroevolution","slug":"an-efficient-application-of-neuroevolution","title":"An Efficient Application of Neuroevolution for Competitive Multiagent Learning","date":"2021-05-23","arxiv_id":"2105.10907","repositories_listed":1,"syntology":null},{"url":"/paper/continual-world-a-robotic-benchmark-for","slug":"continual-world-a-robotic-benchmark-for","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","date":"2021-05-23","arxiv_id":"2105.10919","repositories_listed":1,"syntology":null},{"url":"/paper/cooperative-multi-agent-reinforcement-5","slug":"cooperative-multi-agent-reinforcement-5","title":"Cooperative Multi-Agent Reinforcement Learning with Sequential Credit Assignment","date":"2021-05-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ensemble-quantile-networks-uncertainty-aware","slug":"ensemble-quantile-networks-uncertainty-aware","title":"Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Driving","date":"2021-05-21","arxiv_id":"2105.10266","repositories_listed":1,"syntology":null},{"url":"/paper/offline-meta-reinforcement-learning-1","slug":"offline-meta-reinforcement-learning-1","title":"Offline Meta Reinforcement Learning -- Identifiability Challenges and Effective Data Collection Strategies","date":"2021-05-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/rule-augmented-unsupervised-constituency","slug":"rule-augmented-unsupervised-constituency","title":"Rule Augmented Unsupervised Constituency Parsing","date":"2021-05-21","arxiv_id":"2105.10193","repositories_listed":1,"syntology":null},{"url":"/paper/minimum-delay-adaptation-in-non-stationary","slug":"minimum-delay-adaptation-in-non-stationary","title":"Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection","date":"2021-05-20","arxiv_id":"2105.09452","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/minimum-delay-adaptation-in-non-stationary#ran","syntology_url":"https://syntology.ai/paper/2105.09452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.09452"}},"official":{"repos":["LucasAlegre/mbcd"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-reinforcement-learning-for-optimal-3","slug":"deep-reinforcement-learning-for-optimal-3","title":"Deep Reinforcement Learning for Optimal Stopping with Application in Financial Engineering","date":"2021-05-19","arxiv_id":"2105.08877","repositories_listed":1,"syntology":null},{"url":"/paper/coach-player-multi-agent-reinforcement","slug":"coach-player-multi-agent-reinforcement","title":"Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition","date":"2021-05-18","arxiv_id":"2105.08692","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/coach-player-multi-agent-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2105.08692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08692"}},"official":{"repos":["cranial-xix/marl-copa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-reinforcement-learning-by-tracking-task","slug":"meta-reinforcement-learning-by-tracking-task","title":"Meta-Reinforcement Learning by Tracking Task Non-stationarity","date":"2021-05-18","arxiv_id":"2105.08834","repositories_listed":1,"syntology":null},{"url":"/paper/behavior-based-neuroevolutionary-training-in","slug":"behavior-based-neuroevolutionary-training-in","title":"Behavior-based Neuroevolutionary Training in Reinforcement Learning","date":"2021-05-17","arxiv_id":"2105.07960","repositories_listed":1,"syntology":null},{"url":"/paper/generic-itemset-mining-based-on-reinforcement","slug":"generic-itemset-mining-based-on-reinforcement","title":"Generic Itemset Mining Based on Reinforcement Learning","date":"2021-05-17","arxiv_id":"2105.07753","repositories_listed":1,"syntology":null},{"url":"/paper/regret-minimization-experience-replay","slug":"regret-minimization-experience-replay","title":"Regret Minimization Experience Replay in Off-Policy Reinforcement Learning","date":"2021-05-15","arxiv_id":"2105.07253","repositories_listed":1,"syntology":null},{"url":"/paper/ordering-based-causal-discovery-with-1","slug":"ordering-based-causal-discovery-with-1","title":"Ordering-Based Causal Discovery with Reinforcement Learning","date":"2021-05-14","arxiv_id":"2105.06631","repositories_listed":1,"syntology":null}],"record_sha256":"de3234f7814463c8b6e56d95e1ac377513c96644b73f5d4c856c69b01d4b01eb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}