{"total":55,"rows":[{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2207.05738","title":"PAC Reinforcement Learning for Predictive State Representations","created":"2022-07-12","cited_by_count":43,"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":"2206.03446","title":"Learning in Observable POMDPs, without Computationally Intractable Oracles","created":"2022-06-07","cited_by_count":30,"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":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27,"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":"2303.01566","title":"On the Provable Advantage of Unsupervised Pretraining","created":"2023-03-02","cited_by_count":22,"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":"2305.18258","title":"Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration","created":"2023-05-29","cited_by_count":20,"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":"2302.02252","title":"Reinforcement Learning in Low-Rank MDPs with Density Features","created":"2023-02-04","cited_by_count":18,"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":"2302.01333","title":"Lower Bounds for Learning in Revealing POMDPs","created":"2023-02-02","cited_by_count":15,"area":null},{"id":"2305.11283","title":"On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation","created":"2023-05-18","cited_by_count":14,"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":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2410.05117","title":"Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability","created":"2024-10-07","cited_by_count":12,"area":null},{"id":"2302.02061","title":"Reinforcement Learning with History-Dependent Dynamic Contexts","created":"2023-02-04","cited_by_count":11,"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":"2211.14932","title":"Eluder-based Regret for Stochastic Contextual MDPs","created":"2022-11-27","cited_by_count":9,"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":"2209.14997","title":"Optimistic MLE -- A Generic Model-based Algorithm for Partially Observable Sequential Decision Making","created":"2022-09-29","cited_by_count":6,"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":"2307.00405","title":"Provably Efficient UCB-type Algorithms For Learning Predictive State Representations","created":"2023-07-01","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":"2406.01389","title":"RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"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":"2307.02884","title":"Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight","created":"2023-07-06","cited_by_count":4,"area":null},{"id":"2310.07596","title":"Prospective Side Information for Latent MDPs","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2408.06542","title":"Value of Information and Reward Specification in Active Inference and POMDPs","created":"2024-08-13","cited_by_count":4,"area":null},{"id":"2501.13312","title":"Tensor-Var: Efficient Four-Dimensional Variational Data Assimilation","created":"2025-01-23","cited_by_count":4,"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":"2502.02331","title":"On the Impact of Performative Risk Minimization for Binary Random Variables","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2601.09825","title":"Eluder dimension: localise it!","created":"2026-01-14","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":"2507.09742","title":"Causality-informed Anomaly Detection in Partially Observable Sensor Networks: Moving beyond Correlations","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2310.06243","title":"Sample-Efficient Multi-Agent RL: An Optimization Perspective","created":"2023-10-10","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":"2504.04505","title":"A Classification View on Meta Learning Bandits","created":"2025-04-06","cited_by_count":1,"area":null},{"id":"2505.16547","title":"Find the Fruit: Zero-Shot Sim2Real RL for Occlusion-Aware Plant Manipulation","created":"2025-05-22","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":"2601.18930","title":"Toward Learning POMDPs Beyond Full-Rank Actions and State Observability","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2306.08762","title":"Near-Optimal Partially Observable Reinforcement Learning with Partial Online State Information","created":"2023-06-14","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":"2312.00727","title":"Safe Reinforcement Learning in Tensor Reproducing Kernel Hilbert Space","created":"2023-12-01","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":"2504.16115","title":"A Framework for Objective-Driven Dynamical Stochastic Fields","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2506.09940","title":"The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability","created":"2025-06-11","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":"2606.18393","title":"Learning-Based Decision Making for Combustion Phasing Control in Multi-Fuel CI Engines with Latent Fuel Reactivity Estimation","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2609.39351","title":"On the Complexity of Preference-Based Bandits","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}