{"total":23,"rows":[{"id":"2101.08862","title":"Breaking the Deadly Triad with a Target Network","created":"2021-01-21","cited_by_count":47,"area":null},{"id":"2102.05261","title":"Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States","created":"2021-02-10","cited_by_count":43,"area":null},{"id":"2205.05800","title":"Stochastic first-order methods for average-reward Markov decision processes","created":"2022-05-11","cited_by_count":32,"area":null},{"id":"2101.02808","title":"Average-Reward Off-Policy Policy Evaluation with Function Approximation","created":"2021-01-08","cited_by_count":31,"area":null},{"id":"2106.07329","title":"On-Policy Deep Reinforcement Learning for the Average-Reward Criterion","created":"2021-06-14","cited_by_count":30,"area":null},{"id":"2206.02371","title":"Markovian Interference in Experiments","created":"2022-06-06","cited_by_count":22,"area":null},{"id":"2301.00858","title":"Robust Average-Reward Markov Decision Processes","created":"2023-01-02","cited_by_count":22,"area":null},{"id":"2305.10504","title":"Model-Free Robust Average-Reward Reinforcement Learning","created":"2023-05-17","cited_by_count":20,"area":null},{"id":"2106.03442","title":"Average-Reward Reinforcement Learning with Trust Region Methods","created":"2021-06-07","cited_by_count":19,"area":null},{"id":"2203.03535","title":"Influencing Long-Term Behavior in Multiagent Reinforcement Learning","created":"2022-03-07","cited_by_count":18,"area":null},{"id":"2301.11721","title":"Single-Trajectory Distributionally Robust Reinforcement Learning","created":"2023-01-27","cited_by_count":16,"area":null},{"id":"2112.07066","title":"Continual Learning In Environments With Polynomial Mixing Times","created":"2021-12-13","cited_by_count":14,"area":null},{"id":"2310.02147","title":"Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation","created":"2023-10-03","cited_by_count":14,"area":null},{"id":"2110.13855","title":"Average-Reward Learning and Planning with Options","created":"2021-10-26","cited_by_count":8,"area":null},{"id":"2302.01450","title":"Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms","created":"2023-02-02","cited_by_count":7,"area":null},{"id":"2209.15141","title":"On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly Communicating MDPs","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2410.13563","title":"Ornstein-Uhlenbeck Adaptation as a Mechanism for Learning in Brains and Machines","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2304.03729","title":"Full Gradient Deep Reinforcement Learning for Average-Reward Criterion","created":"2023-04-07","cited_by_count":5,"area":null},{"id":"2302.00808","title":"ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints","created":"2023-02-02","cited_by_count":4,"area":null},{"id":"2204.11897","title":"Reinforcement Teaching","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2602.00474","title":"Persistent-Transient Policy Evaluation for Markov Chains via Minimal Peripheral Quotients","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2608.15966","title":"A Banach-Space Theory of Markovian Halpern Iteration for Non-Expansive Maps","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2306.01896","title":"Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces","created":"2023-06-02","cited_by_count":0,"area":null}],"next_cursor":null}