{"total":42,"rows":[{"id":"2204.08967","title":"When Is Partially Observable Reinforcement Learning Not Scary?","created":"2022-04-19","cited_by_count":100,"area":null},{"id":"2102.04939","title":"RL for Latent MDPs: Regret Guarantees and a Lower Bound","created":"2021-02-09","cited_by_count":70,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2207.05738","title":"PAC Reinforcement Learning for Predictive State Representations","created":"2022-07-12","cited_by_count":43,"area":null},{"id":"2202.03983","title":"Provable Reinforcement Learning with a Short-Term Memory","created":"2022-02-08","cited_by_count":40,"area":null},{"id":"2206.12020","title":"Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems","created":"2022-06-24","cited_by_count":35,"area":null},{"id":"2206.01315","title":"Sample-Efficient Reinforcement Learning of Partially Observable Markov Games","created":"2022-06-02","cited_by_count":27,"area":null},{"id":"2201.04735","title":"Planning in Observable POMDPs in Quasipolynomial Time","created":"2022-01-12","cited_by_count":25,"area":null},{"id":"2209.14990","title":"Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms","created":"2022-09-29","cited_by_count":24,"area":null},{"id":"2207.13081","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","created":"2022-07-26","cited_by_count":21,"area":null},{"id":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20,"area":null},{"id":"2107.03635","title":"Sublinear Regret for Learning POMDPs","created":"2021-07-08","cited_by_count":19,"area":null},{"id":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","cited_by_count":19,"area":null},{"id":"2301.13857","title":"Learning in POMDPs is Sample-Efficient with Hindsight Observability","created":"2023-01-31","cited_by_count":18,"area":null},{"id":"2203.06803","title":"Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits","created":"2022-03-14","cited_by_count":17,"area":null},{"id":"2201.09736","title":"Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learning","created":"2022-01-21","cited_by_count":16,"area":null},{"id":"2204.09787","title":"Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency","created":"2022-04-20","cited_by_count":16,"area":null},{"id":"2205.13476","title":"Embed to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency","created":"2022-05-26","cited_by_count":16,"area":null},{"id":"2206.12081","title":"Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings","created":"2022-06-24","cited_by_count":12,"area":null},{"id":"2311.12244","title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2402.14703","title":"On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation","created":"2024-02-22","cited_by_count":10,"area":null},{"id":"2306.00406","title":"Faster Robust Tensor Power Method for Arbitrary Order","created":"2023-06-01","cited_by_count":8,"area":null},{"id":"2306.12356","title":"Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2110.14524","title":"Model based Multi-agent Reinforcement Learning with Tensor Decompositions","created":"2021-10-27","cited_by_count":7,"area":null},{"id":"2107.07394","title":"Explore and Control with Adversarial Surprise","created":"2021-07-12","cited_by_count":6,"area":null},{"id":"2307.00405","title":"Provably Efficient UCB-type Algorithms For Learning Predictive State Representations","created":"2023-07-01","cited_by_count":6,"area":null},{"id":"2406.01389","title":"RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2510.06540","title":"Scalable Policy-Based RL Algorithms for POMDPs","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2210.03528","title":"Tractable Optimality in Episodic Latent MABs","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2406.07920","title":"Near-Optimal Learning and Planning in Separated Latent MDPs","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2305.00654","title":"Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition","created":"2023-05-01","cited_by_count":2,"area":null},{"id":"2104.00385","title":"Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures","created":"2021-04-01","cited_by_count":1,"area":null},{"id":"2112.14657","title":"Dynamic programming with incomplete information to overcome navigational uncertainty in a nautical environment","created":"2021-12-29","cited_by_count":1,"area":null},{"id":"2410.01331","title":"Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2506.01324","title":"Near-Optimal Clustering in Mixture of Markov Chains","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2601.18930","title":"Toward Learning POMDPs Beyond Full-Rank Actions and State Observability","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2308.02391","title":"Learning Optimal Admission Control in Partially Observable Queueing Networks","created":"2023-08-04","cited_by_count":0,"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":"2501.18790","title":"Achieving $\\widetilde{\\mathcal{O}}(\\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2512.11082","title":"Memoryless Policy Iteration for Episodic POMDPs","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2602.05139","title":"Adaptive Exploration for Latent-State Bandits","created":"2026-02-04","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}],"next_cursor":null}