{"total":16,"rows":[{"id":"2401.13884","title":"Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation","created":"2024-01-25","cited_by_count":17,"area":"deeprl"},{"id":"2501.19254","title":"Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set","created":"2025-01-31","cited_by_count":12,"area":"deeprl"},{"id":"2411.07591","title":"Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization","created":"2024-11-12","cited_by_count":6,"area":"deeprl"},{"id":"2405.15920","title":"SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning","created":"2024-05-24","cited_by_count":5,"area":"deeprl"},{"id":"2509.26442","title":"Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement Learning","created":"2025-09-30","cited_by_count":5,"area":"deeprl"},{"id":"2405.04017","title":"An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks","created":"2024-05-07","cited_by_count":4,"area":"deeprl"},{"id":"2401.15196","title":"Regularized Q-Learning with Linear Function Approximation","created":"2024-01-26","cited_by_count":2,"area":"deeprl"},{"id":"2406.13633","title":"Infinite-Horizon Reinforcement Learning with Multinomial Logistic Function Approximation","created":"2024-06-19","cited_by_count":2,"area":"deeprl"},{"id":"2506.22851","title":"Deep neural networks can provably solve Bellman equations for Markov decision processes without the curse of dimensionality","created":"2025-06-28","cited_by_count":1,"area":"deeprl"},{"id":"2510.19199","title":"A Communication-Efficient Decentralized Actor-Critic Algorithm","created":"2025-10-22","cited_by_count":1,"area":"deeprl"},{"id":"2408.06945","title":"Heavy-Ball Momentum Accelerated Actor-Critic With Function Approximation","created":"2024-08-13","cited_by_count":0,"area":"deeprl"},{"id":"2503.09391","title":"Context-aware Constrained Reinforcement Learning Based Energy-Efficient Power Scheduling for Non-stationary XR Data Traffic","created":"2025-03-12","cited_by_count":0,"area":"deeprl"},{"id":"2510.20748","title":"Reinforcement Learning and Consumption-Savings Behavior","created":"2025-10-23","cited_by_count":0,"area":"deeprl"},{"id":"2511.16226","title":"Deep SOR Minimax Q-learning for Two-player Zero-sum Game","created":"2025-11-20","cited_by_count":0,"area":"deeprl"},{"id":"2601.18907","title":"Implicit Q-Learning and SARSA: Liberating Policy Control from Step-Size Calibration","created":"2026-01-26","cited_by_count":0,"area":"deeprl"},{"id":"2605.06373","title":"Beyond the Independence Assumption: Finite-Sample Guarantees for Deep Q-Learning under $\\tau$-Mixing","created":"2026-05-07","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}