{"total":19,"rows":[{"id":"2302.01333","title":"Lower Bounds for Learning in Revealing POMDPs","created":"2023-02-02","cited_by_count":15,"area":null},{"id":"2302.10796","title":"Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret","created":"2023-02-21","cited_by_count":9,"area":null},{"id":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2306.14468","title":"A General Framework for Sequential Decision-Making under Adaptivity Constraints","created":"2023-06-26","cited_by_count":6,"area":null},{"id":"2404.12648","title":"Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation","created":"2024-04-19","cited_by_count":6,"area":null},{"id":"2406.12795","title":"The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2504.07527","title":"Supervised Optimism Correction: Be Confident When LLMs Are Sure","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2306.01243","title":"Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2312.04464","title":"Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2310.19861","title":"Posterior Sampling for Competitive RL: Function Approximation and Partial Observation","created":"2023-10-30","cited_by_count":3,"area":null},{"id":"2502.05974","title":"Decision Making in Hybrid Environments: A Model Aggregation Approach","created":"2025-02-09","cited_by_count":3,"area":null},{"id":"2411.06739","title":"Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2602.06014","title":"Optimism Stabilizes Thompson Sampling for Adaptive Inference","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2505.07101","title":"Constrained Online Decision-Making: A Unified Framework","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2506.01919","title":"Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2310.10107","title":"Posterior Sampling-based Online Learning for Episodic POMDPs","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2407.13622","title":"Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2606.02363","title":"Minimax-Optimal Policy Regret in Partially Observable Markov Games","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2609.32048","title":"Interactive Distributionally Robust Multi-Agent Learning with General Function Approximation","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}