{"total":16,"rows":[{"id":"2105.01424","title":"On the Linear convergence of Natural Policy Gradient Algorithm","created":"2021-05-04","cited_by_count":48,"area":null},{"id":"2101.11992","title":"Acting in Delayed Environments with Non-Stationary Markov Policies","created":"2021-01-28","cited_by_count":31,"area":null},{"id":"2302.11381","title":"Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes","created":"2023-02-22","cited_by_count":18,"area":null},{"id":"2201.09457","title":"Homotopic Policy Mirror Descent: Policy Convergence, Implicit Regularization, and Improved Sample Complexity","created":"2022-01-24","cited_by_count":14,"area":null},{"id":"2302.00036","title":"Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor","created":"2023-01-31","cited_by_count":13,"area":null},{"id":"2202.02881","title":"Approximate Policy Iteration with Bisimulation Metrics","created":"2022-02-06","cited_by_count":12,"area":null},{"id":"2202.11133","title":"Continual Auxiliary Task Learning","created":"2022-02-22","cited_by_count":9,"area":null},{"id":"2201.12403","title":"Planning and Learning with Adaptive Lookahead","created":"2022-01-28","cited_by_count":8,"area":null},{"id":"2405.12952","title":"Truncated Variance Reduced Value Iteration","created":"2024-05-21","cited_by_count":8,"area":null},{"id":"2110.02195","title":"TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions","created":"2021-10-05","cited_by_count":7,"area":null},{"id":"2307.06877","title":"The complexity of non-stationary reinforcement learning","created":"2023-07-13","cited_by_count":7,"area":null},{"id":"2206.05809","title":"Geometric Policy Iteration for Markov Decision Processes","created":"2022-06-12","cited_by_count":3,"area":null},{"id":"2505.00795","title":"Howard's Policy Iteration is Subexponential for Deterministic Markov Decision Problems with Rewards of Fixed Bit-size and Arbitrary Discount Factor","created":"2025-05-01","cited_by_count":2,"area":null},{"id":"2503.04203","title":"Geometric Re-Analysis of Classical MDP Solving Algorithms","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2609.40147","title":"Policy Iteration Is Not Strongly Polynomial for Deterministic Markov Decision Processes: The Price of Algorithmic Anarchy","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2306.10587","title":"Acceleration in Policy Optimization","created":"2023-06-18","cited_by_count":0,"area":null}],"next_cursor":null}