{"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/93","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":93,"pages_in_order":132,"rows_per_page":100,"rows":[9201,9300],"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/92","next":"/task/reinforcement-learning/papers/94","papers":[{"url":null,"slug":"qopt-optimistic-value-function","title":"QTRAN++: Improved Value Transformation for Cooperative Multi-Agent Reinforcement Learning","date":"2020-06-22","arxiv_id":"2006.12010","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-sensitive-reinforcement-learning-near","title":"Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret","date":"2020-06-22","arxiv_id":"2006.13827","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-reinforcement-learning-of","title":"Sample-Efficient Reinforcement Learning of Undercomplete POMDPs","date":"2020-06-22","arxiv_id":"2006.12484","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-deep","title":"Hierarchical Reinforcement Learning for Deep Goal Reasoning: An Expressiveness Analysis","date":"2020-06-21","arxiv_id":"2006.11704","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-trembling-hand-perfect-mean-field","title":"Reinforcement Learning for Mean Field Games with Strategic Complementarities","date":"2020-06-21","arxiv_id":"2006.11683","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-optimism-in-model-based-reinforcement","title":"Towards Tractable Optimism in Model-Based Reinforcement Learning","date":"2020-06-21","arxiv_id":"2006.11911","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-safe-reinforcement-learning-with","title":"Accelerating Safe Reinforcement Learning with Constraint-mismatched Policies","date":"2020-06-20","arxiv_id":"2006.11645","repositories_listed":0,"syntology":null},{"url":null,"slug":"entropic-risk-constrained-soft-robust-policy","title":"Entropic Risk Constrained Soft-Robust Policy Optimization","date":"2020-06-20","arxiv_id":"2006.11679","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-approach-for","title":"A Reinforcement Learning Approach for Transient Control of Liquid Rocket Engines","date":"2020-06-19","arxiv_id":"2006.11108","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-to-earn-enabling-coordination-within-a","title":"Learn to Earn: Enabling Coordination within a Ride Hailing Fleet","date":"2020-06-19","arxiv_id":"2006.10904","repositories_listed":0,"syntology":null},{"url":null,"slug":"nrowan-dqn-a-stable-noisy-network-with-noise","title":"NROWAN-DQN: A Stable Noisy Network with Noise Reduction and Online Weight Adjustment for Exploration","date":"2020-06-19","arxiv_id":"2006.10980","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-reward-free-reinforcement-learning-with","title":"On Reward-Free Reinforcement Learning with Linear Function Approximation","date":"2020-06-19","arxiv_id":"2006.11274","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-multi-agent-reinforcement-2","title":"Cooperative Multi-Agent Reinforcement Learning with Partial Observations","date":"2020-06-18","arxiv_id":"2006.10822","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-amidst-lifelong","title":"Deep Reinforcement Learning amidst Lifelong Non-Stationarity","date":"2020-06-18","arxiv_id":"2006.10701","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-recommender-system-via-knowledge","title":"Interactive Recommender System via Knowledge Graph-enhanced Reinforcement Learning","date":"2020-06-18","arxiv_id":"2006.10389","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-adaptive-reinforcement-learning-in","title":"Provably adaptive reinforcement learning in metric spaces","date":"2020-06-18","arxiv_id":"2006.10875","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-estimation-bias-via-weighted-delayed","title":"WD3: Taming the Estimation Bias in Deep Reinforcement Learning","date":"2020-06-18","arxiv_id":"2006.12622","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-evaluation-and-seeking-for-multi-agent","title":"Policy Evaluation and Seeking for Multi-Agent Reinforcement Learning via Best Response","date":"2020-06-17","arxiv_id":"2006.09585","repositories_listed":0,"syntology":null},{"url":null,"slug":"index-selection-for-nosql-database-with-deep","title":"Index Selection for NoSQL Database with Deep Reinforcement Learning","date":"2020-06-16","arxiv_id":"2006.08842","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-embedding-model-based-reinforcement","title":"Model Embedding Model-Based Reinforcement Learning","date":"2020-06-16","arxiv_id":"2006.09234","repositories_listed":0,"syntology":null},{"url":null,"slug":"preference-based-reinforcement-learning-with","title":"Preference-based Reinforcement Learning with Finite-Time Guarantees","date":"2020-06-16","arxiv_id":"2006.08910","repositories_listed":0,"syntology":null},{"url":null,"slug":"rl-cyclegan-reinforcement-learning-aware-1","title":"RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real","date":"2020-06-16","arxiv_id":"2006.09001","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-the-order-batching-and-sequencing","title":"Solving the Order Batching and Sequencing Problem using Deep Reinforcement Learning","date":"2020-06-16","arxiv_id":"2006.09507","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-agnostic-exploration-in-reinforcement","title":"Task-agnostic Exploration in Reinforcement Learning","date":"2020-06-16","arxiv_id":"2006.09497","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-teaching-dimension-of-q-learning","title":"The Sample Complexity of Teaching-by-Reinforcement on Q-Learning","date":"2020-06-16","arxiv_id":"2006.09324","repositories_listed":0,"syntology":null},{"url":null,"slug":"variable-gain-gradient-descent-based","title":"Variable Gain Gradient Descent-based Reinforcement Learning for Robust Optimal Tracking Control of Uncertain Nonlinear System with Input-Constraints","date":"2020-06-15","arxiv_id":"1911.04157","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-supervision-from","title":"Reinforcement Learning with Supervision from Noisy Demonstrations","date":"2020-06-14","arxiv_id":"2006.07808","repositories_listed":0,"syntology":null},{"url":null,"slug":"tackling-morpion-solitaire-with-alphazero","title":"Tackling Morpion Solitaire with AlphaZero-likeRanked Reward Reinforcement Learning","date":"2020-06-14","arxiv_id":"2006.07970","repositories_listed":0,"syntology":null},{"url":null,"slug":"hindsight-expectation-maximization-for-goal","title":"Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning","date":"2020-06-13","arxiv_id":"2006.07549","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-as-iterative-and","title":"Reinforcement Learning as Iterative and Amortised Inference","date":"2020-06-13","arxiv_id":"2006.10524","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-brief-look-at-generalization-in-visual-meta","title":"A Brief Look at Generalization in Visual Meta-Reinforcement Learning","date":"2020-06-12","arxiv_id":"2006.07262","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-worlds-in-reinforcement-learning","title":"Bridging Worlds in Reinforcement Learning with Model-Advantage","date":"2020-06-12","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-neural","title":"Deep Reinforcement Learning for Neural Control","date":"2020-06-12","arxiv_id":"2006.07352","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizing-curricula-for-reinforcement","title":"Generalizing Curricula for Reinforcement Learning","date":"2020-06-12","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-5","title":"Hierarchical reinforcement learning for efficent exploration and transfer","date":"2020-06-12","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"logical-composition-in-lifelong-reinforcement","title":"Logical Composition in Lifelong Reinforcement Learning","date":"2020-06-12","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-reinforcement-learning-robust-to","title":"Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling","date":"2020-06-12","arxiv_id":"2006.07178","repositories_listed":0,"syntology":null},{"url":null,"slug":"potential-field-guided-actor-critic","title":"Potential Field Guided Actor-Critic Reinforcement Learning","date":"2020-06-12","arxiv_id":"2006.06923","repositories_listed":0,"syntology":null},{"url":null,"slug":"starcraft-ii-build-order-optimization-using","title":"StarCraft II Build Order Optimization using Deep Reinforcement Learning and Monte-Carlo Tree Search","date":"2020-06-12","arxiv_id":"2006.10525","repositories_listed":0,"syntology":null},{"url":null,"slug":"systematic-generalisation-through-task","title":"Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learning","date":"2020-06-12","arxiv_id":"2006.08767","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-electric","title":"Deep Reinforcement Learning for Electric Transmission Voltage Control","date":"2020-06-11","arxiv_id":"2006.06728","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-informational-learning-processes","title":"Multi-Agent Informational Learning Processes","date":"2020-06-11","arxiv_id":"2006.06870","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-reinforcement-learning-via","title":"Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation","date":"2020-06-11","arxiv_id":"2006.06135","repositories_listed":0,"syntology":null},{"url":null,"slug":"surveys-without-questions-a-reinforcement","title":"Surveys without Questions: A Reinforcement Learning Approach","date":"2020-06-11","arxiv_id":"2006.06323","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-optical","title":"Deep reinforcement learning for optical systems: A case study of mode-locked lasers","date":"2020-06-10","arxiv_id":"2006.05579","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-and-control-engineering-the","title":"Machine learning and control engineering: The model-free case","date":"2020-06-10","arxiv_id":"2006.05738","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-reinforcement-learning","title":"Self-Supervised Reinforcement Learning for Recommender Systems","date":"2020-06-10","arxiv_id":"2006.05779","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-non-stationarity-on","title":"Transient Non-Stationarity and Generalisation in Deep Reinforcement Learning","date":"2020-06-10","arxiv_id":"2006.05826","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-overall-view-of-key-problems-in","title":"An overall view of key problems in algorithmic trading and recent progress","date":"2020-06-09","arxiv_id":"2006.05515","repositories_listed":0,"syntology":null},{"url":null,"slug":"stealing-deep-reinforcement-learning-models","title":"Stealing Deep Reinforcement Learning Models for Fun and Profit","date":"2020-06-09","arxiv_id":"2006.05032","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-decentralized-policy-gradient-approach-to","title":"A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learning","date":"2020-06-08","arxiv_id":"2006.04338","repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-a-cartpole-system-with","title":"Balancing a CartPole System with Reinforcement Learning -- A Tutorial","date":"2020-06-08","arxiv_id":"2006.04938","repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-upper-confidence-reinforcement-1","title":"Constrained Upper Confidence Reinforcement Learning with Known Dynamics","date":"2020-06-08","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-entropy-model-rollouts-fast-model","title":"Maximum Entropy Model Rollouts: Fast Model Based Policy Optimization without Compounding Errors","date":"2020-06-08","arxiv_id":"2006.04802","repositories_listed":0,"syntology":null},{"url":null,"slug":"stable-reinforcement-learning-with-unbounded","title":"Stable Reinforcement Learning with Unbounded State Space","date":"2020-06-08","arxiv_id":"2006.04353","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-poverty-mapping-using-deep","title":"Efficient Poverty Mapping using Deep Reinforcement Learning","date":"2020-06-07","arxiv_id":"2006.04224","repositories_listed":0,"syntology":null},{"url":null,"slug":"implications-of-human-irrationality-for","title":"Implications of Human Irrationality for Reinforcement Learning","date":"2020-06-07","arxiv_id":"2006.04072","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-model-calibration-with-deep","title":"Real-Time Model Calibration with Deep Reinforcement Learning","date":"2020-06-07","arxiv_id":"2006.04001","repositories_listed":0,"syntology":null},{"url":null,"slug":"skill-discovery-of-coordination-in-multi","title":"Skill Discovery of Coordination in Multi-agent Reinforcement Learning","date":"2020-06-07","arxiv_id":"2006.04021","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-evaluation-of-natural-stochastic","title":"Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning","date":"2020-06-06","arxiv_id":"2006.03886","repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-reinforcement-learning-training","title":"Balancing Reinforcement Learning Training Experiences in Interactive Information Retrieval","date":"2020-06-05","arxiv_id":"2006.03185","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-action-separable-reinforcement-learning","title":"State Action Separable Reinforcement Learning","date":"2020-06-05","arxiv_id":"2006.03713","repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-reinforcement-learning-for","title":"Constrained Reinforcement Learning for Dynamic Optimization under Uncertainty","date":"2020-06-04","arxiv_id":"2006.02750","repositories_listed":0,"syntology":null},{"url":null,"slug":"refined-continuous-control-of-ddpg-actors-via","title":"Refined Continuous Control of DDPG Actors via Parametrised Activation","date":"2020-06-04","arxiv_id":"2006.02818","repositories_listed":0,"syntology":null},{"url":null,"slug":"causality-and-batch-reinforcement-learning","title":"Causality and Batch Reinforcement Learning: Complementary Approaches To Planning In Unknown Domains","date":"2020-06-03","arxiv_id":"2006.02579","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-value-improvement-path-towards-better","title":"The Value-Improvement Path: Towards Better Representations for Reinforcement Learning","date":"2020-06-03","arxiv_id":"2006.02243","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-approach-for-multi-agent-cooperative","title":"A novel approach for multi-agent cooperative pursuit to capture grouped evaders","date":"2020-06-01","arxiv_id":"2006.01022","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-bias-in-face-recognition-using","title":"Mitigating Bias in Face Recognition Using Skewness-Aware Reinforcement Learning","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-reinforcement-learning-with-value","title":"Model-Based Reinforcement Learning with Value-Targeted Regression","date":"2020-06-01","arxiv_id":"2006.01107","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-reinforcement-learning-with-1","title":"Robust Reinforcement Learning with Wasserstein Constraint","date":"2020-06-01","arxiv_id":"2006.00945","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-differential-learning-in-continuous","title":"Temporal-Differential Learning in Continuous Environments","date":"2020-06-01","arxiv_id":"2006.00997","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-residential-energy-management","title":"Intelligent Residential Energy Management System using Deep Reinforcement Learning","date":"2020-05-28","arxiv_id":"2005.14259","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-measure-reinforcement-learning-for","title":"Active Measure Reinforcement Learning for Observation Cost Minimization","date":"2020-05-26","arxiv_id":"2005.12697","repositories_listed":0,"syntology":null},{"url":null,"slug":"anomaly-detection-under-controlled-sensing","title":"Anomaly Detection Under Controlled Sensing Using Actor-Critic Reinforcement Learning","date":"2020-05-26","arxiv_id":"2006.01044","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-intervention-centric-causal-reasoning","title":"Towards intervention-centric causal reasoning in learning agents","date":"2020-05-26","arxiv_id":"2005.12968","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-models-for-automatic","title":"Deep Learning Models for Automatic Summarization","date":"2020-05-25","arxiv_id":"2005.11988","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-power-1","title":"Deep Reinforcement Learning Based Power Allocation for D2D Network","date":"2020-05-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-value-estimation-for-single-task","title":"Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning","date":"2020-05-25","arxiv_id":"2005.12254","repositories_listed":0,"syntology":null},{"url":null,"slug":"generator-and-critic-a-deep-reinforcement","title":"Generator and Critic: A Deep Reinforcement Learning Approach for Slate Re-ranking in E-commerce","date":"2020-05-25","arxiv_id":"2005.12206","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-monitored-reinforcement-learning","title":"Gradient Monitored Reinforcement Learning","date":"2020-05-25","arxiv_id":"2005.12108","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-reinforcement-learning-for-trajectory","title":"Meta-Reinforcement Learning for Trajectory Design in Wireless UAV Networks","date":"2020-05-25","arxiv_id":"2005.12394","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-entropy-for-out-of-distribution","title":"Policy Entropy for Out-of-Distribution Classification","date":"2020-05-25","arxiv_id":"2005.12069","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-iterative","title":"Reinforcement Learning with Iterative Reasoning for Merging in Dense Traffic","date":"2020-05-25","arxiv_id":"2005.11895","repositories_listed":0,"syntology":null},{"url":null,"slug":"gochat-goal-oriented-chatbots-with","title":"GoChat: Goal-oriented Chatbots with Hierarchical Reinforcement Learning","date":"2020-05-24","arxiv_id":"2005.11729","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-free-reinforcement-learning-for-1","title":"Model-free Reinforcement Learning for Stochastic Stackelberg Security Games","date":"2020-05-24","arxiv_id":"2005.11853","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-reinforcement-learning-through","title":"Adaptive Reinforcement Learning through Evolving Self-Modifying Neural Networks","date":"2020-05-22","arxiv_id":"2006.05832","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-human-advice-a","title":"Reinforcement learning with human advice: a survey","date":"2020-05-22","arxiv_id":"2005.11016","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-automated-safety-coverage-and-testing","title":"Towards Automated Safety Coverage and Testing for Autonomous Vehicles with Reinforcement Learning","date":"2020-05-22","arxiv_id":"2005.13976","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-based-decision","title":"A reinforcement learning based decision support system in textile manufacturing process","date":"2020-05-20","arxiv_id":"2005.09867","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-high-level","title":"Deep Reinforcement Learning for High Level Character Control","date":"2020-05-20","arxiv_id":"2005.10391","repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-sample-analysis-of-greedy-gq-with","title":"Finite-sample Analysis of Greedy-GQ with Linear Function Approximation under Markovian Noise","date":"2020-05-20","arxiv_id":"2005.10175","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-and-reasoning-for-robot-dialog-and","title":"Learning and Reasoning for Robot Dialog and Navigation Tasks","date":"2020-05-20","arxiv_id":"2005.09833","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-variable-selection","title":"Reinforcement Learning for Variable Selection in a Branch and Bound Algorithm","date":"2020-05-20","arxiv_id":"2005.10026","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-stage-deep-reinforcement-learning-for","title":"Two-stage Deep Reinforcement Learning for Inverter-based Volt-VAR Control in Active Distribution Networks","date":"2020-05-20","arxiv_id":"2005.11142","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-reinforcement-learning-algorithms","title":"A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments","date":"2020-05-19","arxiv_id":"2005.10619","repositories_listed":0,"syntology":null},{"url":null,"slug":"batch-augmented-multi-agent-reinforcement","title":"Batch-Augmented Multi-Agent Reinforcement Learning for Efficient Traffic Signal Optimization","date":"2020-05-19","arxiv_id":"2005.09624","repositories_listed":0,"syntology":null},{"url":null,"slug":"privileged-information-dropout-in","title":"Privileged Information Dropout in Reinforcement Learning","date":"2020-05-19","arxiv_id":"2005.09220","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-caching-with-space","title":"Reinforcement Learning for Caching with Space-Time Popularity Dynamics","date":"2020-05-19","arxiv_id":"2005.09155","repositories_listed":0,"syntology":null},{"url":null,"slug":"automating-turbulence-modeling-by-multi-agent","title":"Automating Turbulence Modeling by Multi-Agent Reinforcement Learning","date":"2020-05-18","arxiv_id":"2005.09023","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-charging-method-for-effective-li-ion","title":"Optimal Charging Method for Effective Li-ion Battery Life Extension Based on Reinforcement Learning","date":"2020-05-18","arxiv_id":"2005.08770","repositories_listed":0,"syntology":null}],"record_sha256":"3f322b26534914fddde7af873779b75f4a14f99ce8322b437d92a61cad328e3a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}