{"total":9,"rows":[{"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":"2110.11280","title":"Actor-critic is implicitly biased towards high entropy optimal policies","created":"2021-10-21","cited_by_count":13,"area":null},{"id":"2302.11694","title":"Constrained Reinforcement Learning using Distributional Representation for Trustworthy Quadrotor UAV Tracking Control","created":"2023-02-22","cited_by_count":5,"area":null},{"id":"2305.18491","title":"Towards a Better Understanding of Representation Dynamics under TD-learning","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2307.07084","title":"Probabilistic Constrained Reinforcement Learning with Formal Interpretability","created":"2023-07-13","cited_by_count":2,"area":null},{"id":"2107.02711","title":"A Unified Off-Policy Evaluation Approach for General Value Function","created":"2021-07-06","cited_by_count":1,"area":null},{"id":"2310.16326","title":"Reinforcement Learning for SBM Graphon Games with Re-Sampling","created":"2023-10-25","cited_by_count":1,"area":null},{"id":"2201.09857","title":"STOPS: Short-Term-based Volatility-controlled Policy Search and its Global Convergence","created":"2022-01-24","cited_by_count":0,"area":null},{"id":"2302.13087","title":"Gauss-Newton Temporal Difference Learning with Nonlinear Function Approximation","created":"2023-02-25","cited_by_count":0,"area":null}],"next_cursor":null}