{"total":123,"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":"2405.16436","title":"Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer","created":"2024-05-26","cited_by_count":109,"area":"alignment"},{"id":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83,"area":"offlinerl"},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2406.01462","title":"The Importance of Online Data: Understanding Preference Fine-tuning via Coverage","created":"2024-06-03","cited_by_count":55,"area":"alignment"},{"id":"2305.09659","title":"Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage","created":"2023-05-16","cited_by_count":51,"area":"offlinerl"},{"id":"2211.04974","title":"Leveraging Offline Data in Online Reinforcement Learning","created":"2022-11-09","cited_by_count":42,"area":"offlinerl"},{"id":"2305.01738","title":"Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare","created":"2023-05-02","cited_by_count":42,"area":"offlinerl"},{"id":"2404.08495","title":"Dataset Reset Policy Optimization for RLHF","created":"2024-04-12","cited_by_count":41,"area":"alignment"},{"id":"2203.13935","title":"Offline Reinforcement Learning Under Value and Density-Ratio Realizability: The Power of Gaps","created":"2022-03-25","cited_by_count":34,"area":"offlinerl"},{"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":"2211.00716","title":"Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian","created":"2022-11-01","cited_by_count":29,"area":"offlinerl"},{"id":"2306.11700","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","created":"2023-06-20","cited_by_count":28,"area":null},{"id":"2207.00046","title":"Performative Reinforcement Learning","created":"2022-06-30","cited_by_count":27,"area":null},{"id":"2205.13589","title":"Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes","created":"2022-05-26","cited_by_count":26,"area":"offlinerl"},{"id":"2303.02569","title":"Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching","created":"2023-03-05","cited_by_count":24,"area":"offlinerl"},{"id":"2310.04413","title":"Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-10-06","cited_by_count":24,"area":"offlinerl"},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2209.08666","title":"Offline Reinforcement Learning with Instrumental Variables in Confounded Markov Decision Processes","created":"2022-09-18","cited_by_count":19,"area":"offlinerl"},{"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":"2301.03377","title":"Machine Learning for Large-Scale Optimization in 6G Wireless Networks","created":"2023-01-03","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":"2302.02571","title":"Offline Learning in Markov Games with General Function Approximation","created":"2023-02-06","cited_by_count":18,"area":"offlinerl"},{"id":"2405.06192","title":"Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning","created":"2024-05-10","cited_by_count":18,"area":"offlinerl"},{"id":"2211.05311","title":"When is Realizability Sufficient for Off-Policy Reinforcement Learning?","created":"2022-11-10","cited_by_count":17,"area":null},{"id":"2305.12944","title":"Offline Primal-Dual Reinforcement Learning for Linear MDPs","created":"2023-05-22","cited_by_count":17,"area":"offlinerl"},{"id":"2306.11626","title":"Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity","created":"2023-06-20","cited_by_count":17,"area":null},{"id":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","cited_by_count":17,"area":null},{"id":"2305.10282","title":"Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning","created":"2023-05-17","cited_by_count":16,"area":"offlinerl"},{"id":"2406.04274","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","created":"2024-06-06","cited_by_count":16,"area":"alignment"},{"id":"2402.09838","title":"Performative Reinforcement Learning in Gradually Shifting Environments","created":"2024-02-15","cited_by_count":14,"area":"deeprl"},{"id":"2206.05581","title":"Federated Offline Reinforcement Learning","created":"2022-06-11","cited_by_count":13,"area":"offlinerl"},{"id":"2211.02016","title":"Oracle Inequalities for Model Selection in Offline Reinforcement Learning","created":"2022-11-03","cited_by_count":13,"area":"offlinerl"},{"id":"2301.12714","title":"Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning","created":"2023-01-30","cited_by_count":13,"area":"offlinerl"},{"id":"2206.02887","title":"Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2210.00750","title":"Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient","created":"2022-10-03","cited_by_count":12,"area":"offlinerl"},{"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":"2502.01203","title":"KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity","created":"2025-02-03","cited_by_count":11,"area":"alignment"},{"id":"2203.12786","title":"Bellman Residual Orthogonalization for Offline Reinforcement Learning","created":"2022-03-24","cited_by_count":10,"area":"offlinerl"},{"id":"2302.02392","title":"Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage","created":"2023-02-05","cited_by_count":10,"area":"offlinerl"},{"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":"2502.06051","title":"Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits","created":"2025-02-09","cited_by_count":10,"area":"offlinerl"},{"id":"2510.04088","title":"Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees","created":"2025-10-05","cited_by_count":10,"area":"offlinerl"},{"id":"2604.06738","title":"Beyond Pessimism: Offline Learning in KL-regularized Games","created":"2026-04-08","cited_by_count":10,"area":null},{"id":"2306.07818","title":"A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2310.01380","title":"Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning","created":"2023-10-02","cited_by_count":9,"area":"offlinerl"},{"id":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2401.08819","title":"Learning from Sparse Offline Datasets via Conservative Density Estimation","created":"2024-01-16","cited_by_count":9,"area":"offlinerl"},{"id":"2402.01173","title":"Efficient Prompt Caching via Embedding Similarity","created":"2024-02-02","cited_by_count":9,"area":null},{"id":"2412.13862","title":"Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model","created":"2024-12-18","cited_by_count":9,"area":"alignment"},{"id":"2506.08460","title":"MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning","created":"2025-06-10","cited_by_count":9,"area":"offlinerl"},{"id":"2210.12057","title":"Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization","created":"2022-10-21","cited_by_count":8,"area":null},{"id":"2210.15543","title":"Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions","created":"2022-10-27","cited_by_count":8,"area":null},{"id":"2402.08201","title":"Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap","created":"2024-02-13","cited_by_count":8,"area":"deeprl"},{"id":"2203.04236","title":"A Complete Characterization of Linear Estimators for Offline Policy Evaluation","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2212.07486","title":"Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction","created":"2022-12-14","cited_by_count":7,"area":null},{"id":"2310.18715","title":"Robust Offline Reinforcement learning with Heavy-Tailed Rewards","created":"2023-10-28","cited_by_count":7,"area":"offlinerl"},{"id":"2310.19527","title":"On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics","created":"2023-10-30","cited_by_count":6,"area":null},{"id":"2401.03301","title":"On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling, and Beyond","created":"2024-01-06","cited_by_count":6,"area":"offlinerl"},{"id":"2408.04526","title":"Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs","created":"2024-08-08","cited_by_count":6,"area":"offlinerl"},{"id":"2412.10616","title":"Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration","created":"2024-12-13","cited_by_count":6,"area":"alignment"},{"id":"2505.05609","title":"On Corruption-Robustness in Performative Reinforcement Learning","created":"2025-05-08","cited_by_count":6,"area":"deeprl"},{"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":"2302.03770","title":"Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability","created":"2023-02-07","cited_by_count":5,"area":"offlinerl"},{"id":"2310.06268","title":"Bi-Level Offline Policy Optimization with Limited Exploration","created":"2023-10-10","cited_by_count":5,"area":"offlinerl"},{"id":"2403.09701","title":"A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage","created":"2024-03-07","cited_by_count":5,"area":null},{"id":"2503.09561","title":"Strategyproof Reinforcement Learning from Human Feedback","created":"2025-03-12","cited_by_count":5,"area":"alignment"},{"id":"2509.21172","title":"Inverse Reinforcement Learning with Just Classification and a Few Regressions","created":"2025-09-25","cited_by_count":5,"area":"offlinerl"},{"id":"2605.00264","title":"Pessimism-Free Offline Learning in General-Sum Games via KL Regularization","created":"2026-04-30","cited_by_count":5,"area":"offlinerl"},{"id":"2304.12886","title":"What can online reinforcement learning with function approximation benefit from general coverage conditions?","created":"2023-04-25","cited_by_count":4,"area":"offlinerl"},{"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":"2401.00629","title":"Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning","created":"2024-01-01","cited_by_count":4,"area":"offlinerl"},{"id":"2403.07933","title":"Corruption-Robust Offline Two-Player Zero-Sum Markov Games","created":"2024-03-04","cited_by_count":4,"area":null},{"id":"2405.12421","title":"A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback","created":"2024-05-20","cited_by_count":4,"area":"alignment"},{"id":"2406.11686","title":"The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation","created":"2024-06-17","cited_by_count":4,"area":"offlinerl"},{"id":"2410.17538","title":"Primal-Dual Spectral Representation for Off-policy Evaluation","created":"2024-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2502.06777","title":"Learning an Optimal Assortment Policy under Observational Data","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2502.19255","title":"Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective","created":"2025-02-26","cited_by_count":4,"area":"alignment"},{"id":"2505.09496","title":"Reinforcement Learning for Individual Optimal Policy from Heterogeneous Data","created":"2025-05-14","cited_by_count":4,"area":"offlinerl"},{"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":"2301.13152","title":"STEEL: Singularity-aware Reinforcement Learning","created":"2023-01-30","cited_by_count":3,"area":"offlinerl"},{"id":"2302.12780","title":"VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation","created":"2023-02-24","cited_by_count":3,"area":"offlinerl"},{"id":"2403.19462","title":"Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization","created":"2024-03-28","cited_by_count":3,"area":"offlinerl"},{"id":"2409.02747","title":"Tractable Offline Learning of Regular Decision Processes","created":"2024-09-04","cited_by_count":3,"area":"offlinerl"},{"id":"2411.06601","title":"OffLight: An Offline Multi-Agent Reinforcement Learning Framework for Traffic Signal Control","created":"2024-11-10","cited_by_count":3,"area":"offlinerl"},{"id":"2505.21395","title":"Square$\\chi$PO: Differentially Private and Robust $\\chi^2$-Preference Optimization in Offline Direct Alignment","created":"2025-05-27","cited_by_count":3,"area":"alignment"},{"id":"2506.01523","title":"Beyond RLHF: A Unified Theoretical Framework of Alignment","created":"2025-06-02","cited_by_count":3,"area":"alignment"},{"id":"2603.22563","title":"Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modeling","created":"2026-03-23","cited_by_count":3,"area":"alignment"},{"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":"2405.13755","title":"Offline RL via Feature-Occupancy Gradient Ascent","created":"2024-05-22","cited_by_count":2,"area":"offlinerl"},{"id":"2503.03023","title":"Quantum Non-Linear Bandit Optimization","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2503.04010","title":"Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2503.12283","title":"Towards Optimal Offline Reinforcement Learning","created":"2025-03-15","cited_by_count":2,"area":"offlinerl"},{"id":"2510.17391","title":"Finite-Time Bounds for Average-Reward Fitted Q-Iteration","created":"2025-10-20","cited_by_count":2,"area":"offlinerl"},{"id":"2512.18957","title":"Online Robust Reinforcement Learning with General Function Approximation","created":"2025-12-22","cited_by_count":2,"area":"deeprl"},{"id":"2512.23805","title":"Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2302.05534","title":"Robust Knowledge Transfer in Tiered Reinforcement Learning","created":"2023-02-10","cited_by_count":1,"area":null},{"id":"2305.12679","title":"Offline Reinforcement Learning with Additional Covering Distributions","created":"2023-05-22","cited_by_count":1,"area":"offlinerl"},{"id":"2309.16188","title":"Stackelberg Batch Policy Learning","created":"2023-09-28","cited_by_count":1,"area":"offlinerl"}],"next_cursor":"100"}