{"total":21,"rows":[{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2106.10517","title":"A Max-Min Entropy Framework for Reinforcement Learning","created":"2021-06-19","cited_by_count":28,"area":null},{"id":"2110.10719","title":"Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning","created":"2021-10-20","cited_by_count":26,"area":null},{"id":"2102.11866","title":"Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality","created":"2021-02-23","cited_by_count":21,"area":null},{"id":"2206.00833","title":"Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm","created":"2022-06-02","cited_by_count":20,"area":null},{"id":"2106.04096","title":"Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation","created":"2021-06-08","cited_by_count":16,"area":null},{"id":"2110.00304","title":"Divergence-Regularized Multi-Agent Actor-Critic","created":"2021-10-01","cited_by_count":15,"area":null},{"id":"2108.07041","title":"Implicitly Regularized RL with Implicit Q-Values","created":"2021-08-16","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2301.08940","title":"Quasi-optimal Reinforcement Learning with Continuous Actions","created":"2023-01-21","cited_by_count":7,"area":null},{"id":"2201.08300","title":"From Psychological Curiosity to Artificial Curiosity: Curiosity-Driven Learning in Artificial Intelligence Tasks","created":"2022-01-20","cited_by_count":6,"area":null},{"id":"2102.10616","title":"Dealing with Non-Stationarity in MARL via Trust-Region Decomposition","created":"2021-02-21","cited_by_count":5,"area":null},{"id":"2107.05217","title":"Cautious Actor-Critic","created":"2021-07-12","cited_by_count":3,"area":null},{"id":"2112.02045","title":"An Analytical Update Rule for General Policy Optimization","created":"2021-12-03","cited_by_count":3,"area":null},{"id":"2202.10506","title":"Accelerating Primal-dual Methods for Regularized Markov Decision Processes","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2107.07659","title":"Geometric Value Iteration: Dynamic Error-Aware KL Regularization for Reinforcement Learning","created":"2021-07-16","cited_by_count":1,"area":null},{"id":"2111.14204","title":"Count-Based Temperature Scheduling for Maximum Entropy Reinforcement Learning","created":"2021-11-28","cited_by_count":1,"area":null},{"id":"2301.08442","title":"Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning","created":"2023-01-20","cited_by_count":1,"area":null},{"id":"2107.05798","title":"Cautious Policy Programming: Exploiting KL Regularization in Monotonic Policy Improvement for Reinforcement Learning","created":"2021-07-13","cited_by_count":0,"area":null},{"id":"2208.02362","title":"Bayesian regularization of empirical MDPs","created":"2022-08-03","cited_by_count":0,"area":null},{"id":"2602.06627","title":"Trust Regions Sell, But Who's Buying? Overlap Geometry as an Alternative Trust Region for Policy Optimization","created":"2026-02-06","cited_by_count":0,"area":null}],"next_cursor":null}