{"total":114,"rows":[{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"area":null},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2305.16589","title":"The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model","created":"2023-05-26","cited_by_count":52,"area":null},{"id":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45,"area":null},{"id":"2202.07511","title":"Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets","created":"2022-02-15","cited_by_count":44,"area":null},{"id":"2106.02757","title":"Heuristic-Guided Reinforcement Learning","created":"2021-06-05","cited_by_count":42,"area":null},{"id":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42,"area":null},{"id":"2106.11960","title":"Variance-Aware Off-Policy Evaluation with Linear Function Approximation","created":"2021-06-22","cited_by_count":34,"area":null},{"id":"2201.06169","title":"On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation","created":"2022-01-17","cited_by_count":33,"area":null},{"id":"2212.09900","title":"Policy learning \"without\" overlap: Pessimism and generalized empirical Bernstein's inequality","created":"2022-12-19","cited_by_count":32,"area":null},{"id":"2211.11349","title":"Data-Driven Offline Decision-Making via Invariant Representation Learning","created":"2022-11-21","cited_by_count":31,"area":null},{"id":"2206.05900","title":"Provable Benefit of Multitask Representation Learning in Reinforcement Learning","created":"2022-06-13","cited_by_count":29,"area":null},{"id":"2104.02293","title":"On the Optimality of Batch Policy Optimization Algorithms","created":"2021-04-06","cited_by_count":28,"area":null},{"id":"2201.03522","title":"When is Offline Two-Player Zero-Sum Markov Game Solvable?","created":"2022-01-10","cited_by_count":28,"area":null},{"id":"2105.03863","title":"Towards Theoretical Understandings of Robust Markov Decision Processes: Sample Complexity and Asymptotics","created":"2021-05-09","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":"2112.13521","title":"Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers?","created":"2021-12-27","cited_by_count":24,"area":null},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2202.13536","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","created":"2022-02-28","cited_by_count":23,"area":null},{"id":"2105.02344","title":"Policy Learning with Adaptively Collected Data","created":"2021-05-05","cited_by_count":21,"area":null},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","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":"2306.02003","title":"On Optimal Caching and Model Multiplexing for Large Model Inference","created":"2023-06-03","cited_by_count":20,"area":null},{"id":"2205.10671","title":"Pessimism for Offline Linear Contextual Bandits using $\\ell_p$ Confidence Sets","created":"2022-05-21","cited_by_count":18,"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":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2205.15827","title":"Robust Anytime Learning of Markov Decision Processes","created":"2022-05-31","cited_by_count":16,"area":null},{"id":"2305.19001","title":"High-probability sample complexities for policy evaluation with linear function approximation","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2405.14335","title":"Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning","created":"2024-05-23","cited_by_count":16,"area":null},{"id":"2304.08944","title":"Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning","created":"2023-04-18","cited_by_count":15,"area":null},{"id":"2403.11574","title":"Offline Multitask Representation Learning for Reinforcement Learning","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2206.00165","title":"Byzantine-Robust Online and Offline Distributed Reinforcement Learning","created":"2022-06-01","cited_by_count":13,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2209.09845","title":"Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL","created":"2022-09-20","cited_by_count":12,"area":null},{"id":"2301.04939","title":"Safe Policy Improvement for POMDPs via Finite-State Controllers","created":"2023-01-12","cited_by_count":12,"area":null},{"id":"2112.12320","title":"Model Selection in Batch Policy Optimization","created":"2021-12-23","cited_by_count":11,"area":null},{"id":"2307.04354","title":"Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data","created":"2023-07-10","cited_by_count":11,"area":null},{"id":"2309.00591","title":"Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms","created":"2023-09-01","cited_by_count":10,"area":null},{"id":"2405.21043","title":"Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation","created":"2024-05-31","cited_by_count":10,"area":null},{"id":"2604.06738","title":"Beyond Pessimism: Offline Learning in KL-regularized Games","created":"2026-04-08","cited_by_count":10,"area":null},{"id":"2212.04720","title":"Multi-Task Off-Policy Learning from Bandit Feedback","created":"2022-12-09","cited_by_count":9,"area":null},{"id":"2303.05848","title":"Decision-Making Under Uncertainty: Beyond Probabilities","created":"2023-03-10","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":"2510.03199","title":"Best-of-Majority: Minimax-Optimal Strategy for Pass@$k$ Inference Scaling","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2306.00324","title":"Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning","created":"2023-06-01","cited_by_count":8,"area":null},{"id":"2306.13601","title":"Active Coverage for PAC Reinforcement Learning","created":"2023-06-23","cited_by_count":8,"area":null},{"id":"2107.11533","title":"Combining Online Learning and Offline Learning for Contextual Bandits with Deficient Support","created":"2021-07-24","cited_by_count":7,"area":null},{"id":"2210.14420","title":"Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2311.13589","title":"Risk-sensitive Markov Decision Process and Learning under General Utility Functions","created":"2023-11-22","cited_by_count":7,"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":"2309.13278","title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","created":"2023-09-23","cited_by_count":6,"area":null},{"id":"2406.00317","title":"Combining Experimental and Historical Data for Policy Evaluation","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2412.14297","title":"Distributionally Robust Policy Learning under Concept Drifts","created":"2024-12-18","cited_by_count":6,"area":null},{"id":"2605.13025","title":"Offline Two-Player Zero-Sum Markov Games with KL Regularization","created":"2026-05-13","cited_by_count":6,"area":null},{"id":"2202.12797","title":"Learning Dynamic Mechanisms in Unknown Environments: A Reinforcement Learning Approach","created":"2022-02-25","cited_by_count":5,"area":null},{"id":"2311.01331","title":"Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching","created":"2023-11-02","cited_by_count":5,"area":null},{"id":"2402.08514","title":"Counterfactual Influence in Markov Decision Processes","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2402.14664","title":"Bayesian Off-Policy Evaluation and Learning for Large Action Spaces","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2405.08498","title":"Learning Decision Policies with Instrumental Variables through Double Machine Learning","created":"2024-05-14","cited_by_count":5,"area":null},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2207.08956","title":"Online Learning with Off-Policy Feedback","created":"2022-07-18","cited_by_count":4,"area":null},{"id":"2208.08056","title":"Sampling Through the Lens of Sequential Decision Making","created":"2022-08-17","cited_by_count":4,"area":null},{"id":"2303.00177","title":"Finite-sample Guarantees for Nash Q-learning with Linear Function Approximation","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2305.04819","title":"Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning","created":"2023-05-08","cited_by_count":4,"area":null},{"id":"2307.08840","title":"Bayesian Safe Policy Learning with Chance Constrained Optimization: Application to Military Security Assessment during the Vietnam War","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2403.07933","title":"Corruption-Robust Offline Two-Player Zero-Sum Markov Games","created":"2024-03-04","cited_by_count":4,"area":null},{"id":"2502.06777","title":"Learning an Optimal Assortment Policy under Observational Data","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2605.02141","title":"On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization","created":"2026-05-04","cited_by_count":4,"area":null},{"id":"2205.12418","title":"Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2206.04921","title":"Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality","created":"2022-06-10","cited_by_count":3,"area":null},{"id":"2302.03821","title":"PASTA: Pessimistic Assortment Optimization","created":"2023-02-08","cited_by_count":3,"area":null},{"id":"2310.11531","title":"Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2311.01329","title":"A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories","created":"2023-11-02","cited_by_count":3,"area":null},{"id":"2505.13768","title":"Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2605.09214","title":"Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2106.09973","title":"The Curse of Passive Data Collection in Batch Reinforcement Learning","created":"2021-06-18","cited_by_count":2,"area":null},{"id":"2206.02593","title":"Pessimistic Off-Policy Optimization for Learning to Rank","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2303.11187","title":"A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2309.02994","title":"An Offline Learning Approach to Propagator Models","created":"2023-09-06","cited_by_count":2,"area":null},{"id":"2310.18617","title":"Pessimistic Off-Policy Multi-Objective Optimization","created":"2023-10-28","cited_by_count":2,"area":null},{"id":"2411.04138","title":"NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2510.01693","title":"PASTA: A Unified Framework for Offline Assortment Learning","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2512.21925","title":"Hybrid Combinatorial Multi-armed Bandits with Probabilistically Triggered Arms","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2601.20116","title":"In-Context Reinforcement Learning From Suboptimal Historical Data","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2202.00076","title":"Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration","created":"2022-01-31","cited_by_count":1,"area":null},{"id":"2210.10278","title":"A Reinforcement Learning Approach in Multi-Phase Second-Price Auction Design","created":"2022-10-19","cited_by_count":1,"area":null},{"id":"2210.13396","title":"Offline congestion games: How feedback type affects data coverage requirement","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2302.05534","title":"Robust Knowledge Transfer in Tiered Reinforcement Learning","created":"2023-02-10","cited_by_count":1,"area":null},{"id":"2306.08810","title":"Deep Generative Models for Decision-Making and Control","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2404.12312","title":"A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization","created":"2024-04-18","cited_by_count":1,"area":null},{"id":"2408.07753","title":"How to Solve Contextual Goal-Oriented Problems with Offline Datasets?","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2503.16708","title":"NeuroSep-CP-LCB: A Deep Learning-based Contextual Multi-armed Bandit Algorithm with Uncertainty Quantification for Early Sepsis Prediction","created":"2025-03-20","cited_by_count":1,"area":null},{"id":"2510.07501","title":"Evaluating and Learning Optimal Dynamic Treatment Regimes under Truncation by Death","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2605.09009","title":"Large Language Models for Sequential Decision-Making: Improving In-Context Learning via Supervised Fine-Tuning","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2205.10739","title":"Offline Policy Comparison with Confidence: Benchmarks and Baselines","created":"2022-05-22","cited_by_count":0,"area":null},{"id":"2209.05186","title":"Statistical Estimation of Confounded Linear MDPs: An Instrumental Variable Approach","created":"2022-09-12","cited_by_count":0,"area":null},{"id":"2211.17249","title":"Efficient Reinforcement Learning Through Trajectory Generation","created":"2022-11-30","cited_by_count":0,"area":null}],"next_cursor":"100"}