{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/reinforcement-learning/papers/27","list_of":"/task/reinforcement-learning","task":"Reinforcement Learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":27,"pages_in_order":132,"rows_per_page":100,"rows":[2601,2700],"of":13178,"counts":{"archive_papers_tagged":13178,"with_a_code_link":4183,"where_syntology_ran_a_sample":1175,"not_listed_spam_title":0,"listed":13178,"listed_where_code_ran":1175,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":988,"every_run_a_failure_of_syntologys_instrument":187,"listed_with_a_run_with_no_instrument_failure":988,"listed_every_run_a_failure_of_syntologys_instrument":187,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/reinforcement-learning","prev":"/task/reinforcement-learning/papers/26","next":"/task/reinforcement-learning/papers/28","papers":[{"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/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/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/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},{"url":"/paper/spectral-normalisation-for-deep-reinforcement","slug":"spectral-normalisation-for-deep-reinforcement","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","date":"2021-05-11","arxiv_id":"2105.05246","repositories_listed":1,"syntology":null},{"url":"/paper/a-deep-reinforcement-learning-approach-to-3","slug":"a-deep-reinforcement-learning-approach-to-3","title":"A Deep Reinforcement Learning Approach to Audio-Based Navigation in a Multi-Speaker Environment","date":"2021-05-10","arxiv_id":"2105.04488","repositories_listed":1,"syntology":null},{"url":"/paper/deeprf-deep-reinforcement-learning-designed","slug":"deeprf-deep-reinforcement-learning-designed","title":"Deep reinforcement learning-designed radiofrequency waveform in MRI","date":"2021-05-07","arxiv_id":"2105.03061","repositories_listed":1,"syntology":null},{"url":"/paper/meta-learning-based-deep-reinforcement","slug":"meta-learning-based-deep-reinforcement","title":"Meta-Learning-Based Deep Reinforcement Learning for Multiobjective Optimization Problems","date":"2021-05-06","arxiv_id":"2105.02741","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/meta-learning-based-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2105.02741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.02741"}},"official":{"repos":["zhangzizhen/ml-dam"],"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/model-free-policy-evaluation-in-reinforcement","slug":"model-free-policy-evaluation-in-reinforcement","title":"UVIP: Model-Free Approach to Evaluate Reinforcement Learning Algorithms","date":"2021-05-05","arxiv_id":"2105.02135","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-adaptive-3","slug":"deep-reinforcement-learning-for-adaptive-3","title":"Deep Reinforcement Learning for Adaptive Exploration of Unknown Environments","date":"2021-05-04","arxiv_id":"2105.01606","repositories_listed":1,"syntology":null},{"url":"/paper/robotic-surgery-with-lean-reinforcement","slug":"robotic-surgery-with-lean-reinforcement","title":"Robotic Surgery With Lean Reinforcement Learning","date":"2021-05-03","arxiv_id":"2105.01006","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-to-reward-progressivity-via-spectral-1","slug":"adapting-to-reward-progressivity-via-spectral-1","title":"Adapting to Reward Progressivity via Spectral Reinforcement Learning","date":"2021-04-29","arxiv_id":"2104.14138","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/adapting-to-reward-progressivity-via-spectral-1#ran","syntology_url":"https://syntology.ai/paper/2104.14138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14138"}},"official":{"repos":["mchldann/SpectralDQN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-scalable-and-reproducible-system-on-chip","slug":"a-scalable-and-reproducible-system-on-chip","title":"A Scalable and Reproducible System-on-Chip Simulation for Reinforcement Learning","date":"2021-04-27","arxiv_id":"2104.13187","repositories_listed":1,"syntology":null},{"url":"/paper/computational-performance-of-deep","slug":"computational-performance-of-deep","title":"Computational Performance of Deep Reinforcement Learning to find Nash Equilibria","date":"2021-04-26","arxiv_id":"2104.12895","repositories_listed":1,"syntology":null},{"url":"/paper/constraint-guided-reinforcement-learning","slug":"constraint-guided-reinforcement-learning","title":"Constraint-Guided Reinforcement Learning: Augmenting the Agent-Environment-Interaction","date":"2021-04-24","arxiv_id":"2104.11918","repositories_listed":1,"syntology":null},{"url":"/paper/graph-neural-network-reinforcement-learning","slug":"graph-neural-network-reinforcement-learning","title":"Graph Neural Network Reinforcement Learning for Autonomous Mobility-on-Demand Systems","date":"2021-04-23","arxiv_id":"2104.11434","repositories_listed":1,"syntology":null},{"url":"/paper/safe-chance-constrained-reinforcement","slug":"safe-chance-constrained-reinforcement","title":"Safe Chance Constrained Reinforcement Learning for Batch Process Control","date":"2021-04-23","arxiv_id":"2104.11706","repositories_listed":1,"syntology":null},{"url":"/paper/a-learning-gap-between-neuroscience-and","slug":"a-learning-gap-between-neuroscience-and","title":"A learning gap between neuroscience and reinforcement learning","date":"2021-04-22","arxiv_id":"2104.10995","repositories_listed":1,"syntology":null},{"url":"/paper/independent-reinforcement-learning-for-weakly","slug":"independent-reinforcement-learning-for-weakly","title":"Independent Reinforcement Learning for Weakly Cooperative Multiagent Traffic Control Problem","date":"2021-04-22","arxiv_id":"2104.10917","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-mixture-of-experts-for-1","slug":"probabilistic-mixture-of-experts-for-1","title":"Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning","date":"2021-04-19","arxiv_id":"2104.09122","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/probabilistic-mixture-of-experts-for-1#ran","syntology_url":"https://syntology.ai/paper/2104.09122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09122"}},"official":{"repos":["JieRen98/rlkit-pmoe"],"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/keyphrase-generation-with-fine-grained","slug":"keyphrase-generation-with-fine-grained","title":"Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning","date":"2021-04-18","arxiv_id":"2104.08799","repositories_listed":1,"syntology":null},{"url":"/paper/quick-learner-automated-vehicle-adapting-its","slug":"quick-learner-automated-vehicle-adapting-its","title":"Quick Learner Automated Vehicle Adapting its Roadmanship to Varying Traffic Cultures with Meta Reinforcement Learning","date":"2021-04-18","arxiv_id":"2104.08876","repositories_listed":1,"syntology":null},{"url":"/paper/towards-standardizing-reinforcement-learning","slug":"towards-standardizing-reinforcement-learning","title":"Towards Standardising Reinforcement Learning Approaches for Production Scheduling Problems","date":"2021-04-16","arxiv_id":"2104.08196","repositories_listed":1,"syntology":null},{"url":"/paper/quantum-architecture-search-via-deep","slug":"quantum-architecture-search-via-deep","title":"Quantum Architecture Search via Deep Reinforcement Learning","date":"2021-04-15","arxiv_id":"2104.07715","repositories_listed":1,"syntology":null},{"url":"/paper/a-coevolutionairy-approach-to-deep-multi","slug":"a-coevolutionairy-approach-to-deep-multi","title":"A coevolutionary approach to deep multi-agent reinforcement learning","date":"2021-04-12","arxiv_id":"2104.05610","repositories_listed":1,"syntology":null},{"url":"/paper/the-atari-data-scraper","slug":"the-atari-data-scraper","title":"The Atari Data Scraper","date":"2021-04-11","arxiv_id":"2104.04893","repositories_listed":1,"syntology":null},{"url":"/paper/imperfect-also-deserves-reward-multi-level","slug":"imperfect-also-deserves-reward-multi-level","title":"Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management","date":"2021-04-10","arxiv_id":"2104.04748","repositories_listed":1,"syntology":null},{"url":"/paper/connecting-deep-reinforcement-learning-based","slug":"connecting-deep-reinforcement-learning-based","title":"Connecting Deep-Reinforcement-Learning-based Obstacle Avoidance with Conventional Global Planners using Waypoint Generators","date":"2021-04-08","arxiv_id":"2104.03663","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-time-stepping-for-numerical","slug":"efficient-time-stepping-for-numerical","title":"Efficient time stepping for numerical integration using reinforcement learning","date":"2021-04-08","arxiv_id":"2104.03562","repositories_listed":1,"syntology":null},{"url":"/paper/optimal-market-making-by-reinforcement","slug":"optimal-market-making-by-reinforcement","title":"Optimal Market Making by Reinforcement Learning","date":"2021-04-08","arxiv_id":"2104.04036","repositories_listed":1,"syntology":null},{"url":"/paper/towards-deployment-of-deep-reinforcement","slug":"towards-deployment-of-deep-reinforcement","title":"Arena-Rosnav: Towards Deployment of Deep-Reinforcement-Learning-Based Obstacle Avoidance into Conventional Autonomous Navigation Systems","date":"2021-04-08","arxiv_id":"2104.03616","repositories_listed":1,"syntology":null},{"url":"/paper/design-and-implementation-of-an-environment","slug":"design-and-implementation-of-an-environment","title":"Design and implementation of an environment for Learning to Run a Power Network (L2RPN)","date":"2021-04-06","arxiv_id":"2104.04080","repositories_listed":1,"syntology":null},{"url":"/paper/c-coma-a-continual-reinforcement-learning","slug":"c-coma-a-continual-reinforcement-learning","title":"C-COMA: A CONTINUAL REINFORCEMENT LEARNING MODEL FOR DYNAMIC MULTIAGENT ENVIRONMENTS","date":"2021-04-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/influencing-reinforcement-learning-through","slug":"influencing-reinforcement-learning-through","title":"Influencing Reinforcement Learning through Natural Language Guidance","date":"2021-04-04","arxiv_id":"2104.01506","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-resource-1","slug":"deep-reinforcement-learning-for-resource-1","title":"Deep Reinforcement Learning for Resource Allocation in Business Processes","date":"2021-03-29","arxiv_id":"2104.00541","repositories_listed":1,"syntology":null},{"url":"/paper/robust-reinforcement-learning-under-model","slug":"robust-reinforcement-learning-under-model","title":"Robust Reinforcement Learning under model misspecification","date":"2021-03-29","arxiv_id":"2103.15370","repositories_listed":1,"syntology":null},{"url":"/paper/shaping-advice-in-deep-multi-agent","slug":"shaping-advice-in-deep-multi-agent","title":"Shaping Advice in Deep Multi-Agent Reinforcement Learning","date":"2021-03-29","arxiv_id":"2103.15941","repositories_listed":1,"syntology":null},{"url":"/paper/self-adaptive-torque-vectoring-controller","slug":"self-adaptive-torque-vectoring-controller","title":"Self-adaptive Torque Vectoring Controller Using Reinforcement Learning","date":"2021-03-27","arxiv_id":"2103.14892","repositories_listed":1,"syntology":null},{"url":"/paper/model-predictive-actor-critic-accelerating","slug":"model-predictive-actor-critic-accelerating","title":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","date":"2021-03-25","arxiv_id":"2103.13842","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/model-predictive-actor-critic-accelerating#ran","syntology_url":"https://syntology.ai/paper/2103.13842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13842"}},"official":{"repos":["dnandha/mopac"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-practical-guide-to-multi-objective","slug":"a-practical-guide-to-multi-objective","title":"A Practical Guide to Multi-Objective Reinforcement Learning and Planning","date":"2021-03-17","arxiv_id":"2103.09568","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-reinforcement-learning-for-1","slug":"weakly-supervised-reinforcement-learning-for-1","title":"Weakly Supervised Reinforcement Learning for Autonomous Highway Driving via Virtual Safety Cages","date":"2021-03-17","arxiv_id":"2103.09726","repositories_listed":1,"syntology":null},{"url":"/paper/inclined-quadrotor-landing-using-deep","slug":"inclined-quadrotor-landing-using-deep","title":"Inclined Quadrotor Landing using Deep Reinforcement Learning","date":"2021-03-16","arxiv_id":"2103.09043","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-band","slug":"deep-reinforcement-learning-for-band","title":"Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classification","date":"2021-03-15","arxiv_id":"2103.08741","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-algorithms-from","slug":"reinforcement-learning-with-algorithms-from","title":"Reinforcement Learning with Algorithms from Probabilistic Structure Estimation","date":"2021-03-15","arxiv_id":"2103.08241","repositories_listed":1,"syntology":null},{"url":"/paper/solving-compositional-reinforcement-learning-1","slug":"solving-compositional-reinforcement-learning-1","title":"Solving Compositional Reinforcement Learning Problems via Task Reduction","date":"2021-03-13","arxiv_id":"2103.07607","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/solving-compositional-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2103.07607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07607"}},"official":{"repos":["IrisLi17/self-imitation-via-reduction"],"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/large-batch-simulation-for-deep-reinforcement-1","slug":"large-batch-simulation-for-deep-reinforcement-1","title":"Large Batch Simulation for Deep Reinforcement Learning","date":"2021-03-12","arxiv_id":"2103.07013","repositories_listed":1,"syntology":null},{"url":"/paper/a-quadratic-actor-network-for-model-free","slug":"a-quadratic-actor-network-for-model-free","title":"A Quadratic Actor Network for Model-Free Reinforcement Learning","date":"2021-03-11","arxiv_id":"2103.06617","repositories_listed":1,"syntology":null},{"url":"/paper/generalizable-episodic-memory-for-deep","slug":"generalizable-episodic-memory-for-deep","title":"Generalizable Episodic Memory for Deep Reinforcement Learning","date":"2021-03-11","arxiv_id":"2103.06469","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalizable-episodic-memory-for-deep#ran","syntology_url":"https://syntology.ai/paper/2103.06469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06469"}},"official":{"repos":["MouseHu/GEM"],"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/policy-search-with-rare-significant-events","slug":"policy-search-with-rare-significant-events","title":"Policy Search with Rare Significant Events: Choosing the Right Partner to Cooperate with","date":"2021-03-11","arxiv_id":"2103.06846","repositories_listed":1,"syntology":null},{"url":"/paper/iterative-shrinking-for-referring-expression","slug":"iterative-shrinking-for-referring-expression","title":"Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning","date":"2021-03-09","arxiv_id":"2103.05187","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-prototypical-1","slug":"reinforcement-learning-with-prototypical-1","title":"Reinforcement Learning with Prototypical Representations","date":"2021-03-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-ai-arena-a-framework-for-distributed","slug":"the-ai-arena-a-framework-for-distributed","title":"The AI Arena: A Framework for Distributed Multi-Agent Reinforcement Learning","date":"2021-03-09","arxiv_id":"2103.05737","repositories_listed":1,"syntology":null},{"url":"/paper/a-crash-course-on-reinforcement-learning","slug":"a-crash-course-on-reinforcement-learning","title":"A Crash Course on Reinforcement Learning","date":"2021-03-08","arxiv_id":"2103.04910","repositories_listed":1,"syntology":null},{"url":"/paper/deepfreight-a-model-free-deep-reinforcement","slug":"deepfreight-a-model-free-deep-reinforcement","title":"DeepFreight: Integrating Deep Reinforcement Learning and Mixed Integer Programming for Multi-transfer Truck Freight Delivery","date":"2021-03-05","arxiv_id":"2103.03450","repositories_listed":1,"syntology":null},{"url":"/paper/lyapunov-regularized-reinforcement-learning","slug":"lyapunov-regularized-reinforcement-learning","title":"Lyapunov-Regularized Reinforcement Learning for Power System Transient Stability","date":"2021-03-05","arxiv_id":"2103.03869","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-learning-for-robust-fitting-a","slug":"unsupervised-learning-for-robust-fitting-a","title":"Unsupervised Learning for Robust Fitting:A Reinforcement Learning Approach","date":"2021-03-05","arxiv_id":"2103.03501","repositories_listed":1,"syntology":null},{"url":"/paper/improving-computational-efficiency-in-visual","slug":"improving-computational-efficiency-in-visual","title":"Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings","date":"2021-03-04","arxiv_id":"2103.02886","repositories_listed":1,"syntology":null},{"url":"/paper/model-based-safe-reinforcement-learning-using","slug":"model-based-safe-reinforcement-learning-using","title":"Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function","date":"2021-03-02","arxiv_id":"2103.01556","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/model-based-safe-reinforcement-learning-using#ran","syntology_url":"https://syntology.ai/paper/2103.01556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01556"}},"official":{"repos":["mahaitongdae/safe_exp_env"],"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/robot-navigation-in-a-crowd-by-integrating","slug":"robot-navigation-in-a-crowd-by-integrating","title":"Robot Navigation in a Crowd by Integrating Deep Reinforcement Learning and Online Planning","date":"2021-02-26","arxiv_id":"2102.13265","repositories_listed":1,"syntology":null},{"url":"/paper/robust-deep-reinforcement-learning-via-multi","slug":"robust-deep-reinforcement-learning-via-multi","title":"DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck","date":"2021-02-26","arxiv_id":"2102.13268","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-deep-reinforcement-learning-via-multi#ran","syntology_url":"https://syntology.ai/paper/2102.13268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.13268"}},"official":{"repos":["BU-DEPEND-Lab/DRIBO"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/information-directed-reward-learning-for","slug":"information-directed-reward-learning-for","title":"Information Directed Reward Learning for Reinforcement Learning","date":"2021-02-24","arxiv_id":"2102.12466","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/information-directed-reward-learning-for#ran","syntology_url":"https://syntology.ai/paper/2102.12466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12466"}},"official":{"repos":["david-lindner/idrl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/memory-based-deep-reinforcement-learning-for-1","slug":"memory-based-deep-reinforcement-learning-for-1","title":"Memory-based Deep Reinforcement Learning for POMDPs","date":"2021-02-24","arxiv_id":"2102.12344","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/memory-based-deep-reinforcement-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2102.12344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12344"}},"official":{"repos":["LinghengMeng/LSTM-TD3"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/psiphi-learning-reinforcement-learning-with","slug":"psiphi-learning-reinforcement-learning-with","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","date":"2021-02-24","arxiv_id":"2102.12560","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-multimodal-reinforcement-learning","slug":"exploiting-multimodal-reinforcement-learning","title":"Exploiting Multimodal Reinforcement Learning for Simultaneous Machine Translation","date":"2021-02-22","arxiv_id":"2102.11387","repositories_listed":1,"syntology":null},{"url":"/paper/program-synthesis-guided-reinforcement","slug":"program-synthesis-guided-reinforcement","title":"Program Synthesis Guided Reinforcement Learning for Partially Observed Environments","date":"2021-02-22","arxiv_id":"2102.11137","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/program-synthesis-guided-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2102.11137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11137"}},"official":{"repos":["yycdavid/program-synthesis-guided-rl"],"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/reinforcement-learning-with-prototypical","slug":"reinforcement-learning-with-prototypical","title":"Reinforcement Learning with Prototypical Representations","date":"2021-02-22","arxiv_id":"2102.11271","repositories_listed":1,"syntology":null},{"url":"/paper/decaying-clipping-range-in-proximal-policy","slug":"decaying-clipping-range-in-proximal-policy","title":"Decaying Clipping Range in Proximal Policy Optimization","date":"2021-02-20","arxiv_id":"2102.10456","repositories_listed":1,"syntology":null},{"url":"/paper/towards-automatic-evaluation-of-dialog","slug":"towards-automatic-evaluation-of-dialog","title":"Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach","date":"2021-02-20","arxiv_id":"2102.10242","repositories_listed":1,"syntology":null},{"url":"/paper/sim-env-decoupling-openai-gym-environments","slug":"sim-env-decoupling-openai-gym-environments","title":"Sim-Env: Decoupling OpenAI Gym Environments from Simulation Models","date":"2021-02-19","arxiv_id":"2102.09824","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-doubly-constrained-batch","slug":"continuous-doubly-constrained-batch","title":"Continuous Doubly Constrained Batch Reinforcement Learning","date":"2021-02-18","arxiv_id":"2102.09225","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/continuous-doubly-constrained-batch#ran","syntology_url":"https://syntology.ai/paper/2102.09225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.09225"}},"official":{"repos":["amazon-research/cdc-batch-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-agent-reinforcement-learning-of-3d","slug":"multi-agent-reinforcement-learning-of-3d","title":"Multi-Agent Reinforcement Learning of 3D Furniture Layout Simulation in Indoor Graphics Scenes","date":"2021-02-18","arxiv_id":"2102.09137","repositories_listed":1,"syntology":null},{"url":"/paper/seapearl-a-constraint-programming-solver","slug":"seapearl-a-constraint-programming-solver","title":"SeaPearl: A Constraint Programming Solver guided by Reinforcement Learning","date":"2021-02-18","arxiv_id":"2102.09193","repositories_listed":1,"syntology":null},{"url":"/paper/developing-parsimonious-ensembles-using-1","slug":"developing-parsimonious-ensembles-using-1","title":"Developing parsimonious ensembles using predictor diversity within a reinforcement learning framework","date":"2021-02-15","arxiv_id":"2102.07344","repositories_listed":1,"syntology":null},{"url":"/paper/how-rl-agents-behave-when-their-actions-are","slug":"how-rl-agents-behave-when-their-actions-are","title":"How RL Agents Behave When Their Actions Are Modified","date":"2021-02-15","arxiv_id":"2102.07716","repositories_listed":1,"syntology":null},{"url":"/paper/intelligent-electric-vehicle-charging","slug":"intelligent-electric-vehicle-charging","title":"Intelligent Electric Vehicle Charging Recommendation Based on Multi-Agent Reinforcement Learning","date":"2021-02-15","arxiv_id":"2102.07359","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-multi-agent-reinforcement-learning","slug":"scaling-multi-agent-reinforcement-learning","title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","date":"2021-02-15","arxiv_id":"2102.07475","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/scaling-multi-agent-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2102.07475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07475"}},"official":{"repos":["uoe-agents/seps"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/q-value-weighted-regression-reinforcement-1","slug":"q-value-weighted-regression-reinforcement-1","title":"Q-Value Weighted Regression: Reinforcement Learning with Limited Data","date":"2021-02-12","arxiv_id":"2102.06782","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/q-value-weighted-regression-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2102.06782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.06782"}},"official":null}},{"url":"/paper/domain-adaptation-in-reinforcement-learning","slug":"domain-adaptation-in-reinforcement-learning","title":"Domain Adaptation In Reinforcement Learning Via Latent Unified State Representation","date":"2021-02-10","arxiv_id":"2102.05714","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"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 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) · 0 unverified","sample_list":"/paper/domain-adaptation-in-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2102.05714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05714"}},"official":{"repos":["KarlXing/LUSR"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/policy-augmentation-an-exploration-strategy","slug":"policy-augmentation-an-exploration-strategy","title":"Policy Augmentation: An Exploration Strategy for Faster Convergence of Deep Reinforcement Learning Algorithms","date":"2021-02-10","arxiv_id":"2102.05249","repositories_listed":1,"syntology":null},{"url":"/paper/risk-averse-offline-reinforcement-learning-1","slug":"risk-averse-offline-reinforcement-learning-1","title":"Risk-Averse Offline Reinforcement Learning","date":"2021-02-10","arxiv_id":"2102.05371","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-time-model-based-reinforcement","slug":"continuous-time-model-based-reinforcement","title":"Continuous-Time Model-Based Reinforcement Learning","date":"2021-02-09","arxiv_id":"2102.04764","repositories_listed":1,"syntology":null},{"url":"/paper/rl-reach-reproducible-reinforcement-learning","slug":"rl-reach-reproducible-reinforcement-learning","title":"rl_reach: Reproducible Reinforcement Learning Experiments for Robotic Reaching Tasks","date":"2021-02-09","arxiv_id":"2102.04916","repositories_listed":1,"syntology":null},{"url":"/paper/rl-scope-cross-stack-profiling-for-deep","slug":"rl-scope-cross-stack-profiling-for-deep","title":"RL-Scope: Cross-Stack Profiling for Deep Reinforcement Learning Workloads","date":"2021-02-08","arxiv_id":"2102.04285","repositories_listed":1,"syntology":null},{"url":"/paper/sparsely-ensembled-convolutional-neural","slug":"sparsely-ensembled-convolutional-neural","title":"Sparsely ensembled convolutional neural network classifiers via reinforcement learning","date":"2021-02-07","arxiv_id":"2102.03921","repositories_listed":1,"syntology":null}],"record_sha256":"9a11f00661abc54dd8357daaed2a98fb72bd5d4ef6d332a92b929658bf0c1ab1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}