{"total":15,"rows":[{"id":"2101.08862","title":"Breaking the Deadly Triad with a Target Network","created":"2021-01-21","cited_by_count":47,"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":"2206.02371","title":"Markovian Interference in Experiments","created":"2022-06-06","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":"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":"2308.01170","title":"Revisiting a Design Choice in Gradient Temporal Difference Learning","created":"2023-08-02","cited_by_count":7,"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":"2307.15892","title":"A new Gradient TD Algorithm with only One Step-size: Convergence Rate Analysis using $L$-$\\lambda$ Smoothness","created":"2023-07-29","cited_by_count":2,"area":null},{"id":"2406.09563","title":"e-COP : Episodic Constrained Optimization of Policies","created":"2024-06-13","cited_by_count":2,"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":"2306.01896","title":"Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2605.02103","title":"Bridging the Gap Between Average and Discounted TD Learning","created":"2026-05-03","cited_by_count":0,"area":null}],"next_cursor":null}