{"total":17,"rows":[{"id":"2411.03810","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","created":"2024-11-06","cited_by_count":8,"area":"deeprl"},{"id":"2406.13909","title":"Beyond Optimism: Exploration With Partially Observable Rewards","created":"2024-06-20","cited_by_count":6,"area":"deeprl"},{"id":"2505.11478","title":"Automatic Reward Shaping from Confounded Offline Data","created":"2025-05-16","cited_by_count":6,"area":"deeprl"},{"id":"2407.00801","title":"Model-Free Active Exploration in Reinforcement Learning","created":"2024-06-30","cited_by_count":5,"area":"deeprl"},{"id":"2507.14444","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","created":"2025-07-19","cited_by_count":2,"area":"deeprl"},{"id":"2507.12383","title":"Improving Reinforcement Learning Sample-Efficiency using Local Approximation","created":"2025-07-16","cited_by_count":1,"area":"deeprl"},{"id":"2507.22854","title":"A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model","created":"2025-07-30","cited_by_count":1,"area":"deeprl"},{"id":"2509.14077","title":"Online Bayesian Risk-Averse Reinforcement Learning","created":"2025-09-17","cited_by_count":1,"area":"deeprl"},{"id":"2510.03181","title":"Q-Learning with Shift-Aware Upper Confidence Bound in Non-Stationary Reinforcement Learning","created":"2025-10-03","cited_by_count":1,"area":"deeprl"},{"id":"2402.11877","title":"Learning the Model While Learning Q: Finite-Time Sample Complexity of Online SyncMBQ","created":"2024-02-19","cited_by_count":0,"area":"deeprl"},{"id":"2501.13394","title":"Concurrent Learning with Aggregated States via Randomized Least Squares Value Iteration","created":"2025-01-23","cited_by_count":0,"area":"deeprl"},{"id":"2508.13963","title":"Convergent Reinforcement Learning Algorithms for Stochastic Shortest Path Problem","created":"2025-08-19","cited_by_count":0,"area":"deeprl"},{"id":"2511.03595","title":"Tensor-Efficient High-Dimensional Q-learning","created":"2025-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2605.15692","title":"Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning","created":"2026-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2605.24345","title":"Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs","created":"2026-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2607.19854","title":"Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence","created":"2026-07-22","cited_by_count":0,"area":"deeprl"},{"id":"2609.36486","title":"Optimal Multi-Reward Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}