{"total":279,"rows":[{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350,"area":"alignment"},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247,"area":"alignment"},{"id":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164,"area":"offlinerl"},{"id":"2106.04895","title":"Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning","created":"2021-06-09","cited_by_count":158,"area":"offlinerl"},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"2110.04652","title":"Representation Learning for Online and Offline RL in Low-rank MDPs","created":"2021-10-09","cited_by_count":129,"area":"offlinerl"},{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127,"area":"alignment"},{"id":"2202.04634","title":"Offline Reinforcement Learning with Realizability and Single-policy Concentrability","created":"2022-02-09","cited_by_count":123,"area":"offlinerl"},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"id":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112,"area":"offlinerl"},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110,"area":"offlinerl"},{"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":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"area":"offlinerl"},{"id":"2208.05767","title":"Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity","created":"2022-08-11","cited_by_count":87,"area":"offlinerl"},{"id":"2202.13890","title":"Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity","created":"2022-02-28","cited_by_count":85,"area":"offlinerl"},{"id":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84,"area":"offlinerl"},{"id":"2502.12118","title":"Scaling Test-Time Compute Without Verification or RL is Suboptimal","created":"2025-02-17","cited_by_count":84,"area":"lr"},{"id":"2204.05275","title":"Settling the Sample Complexity of Model-Based Offline Reinforcement Learning","created":"2022-04-11","cited_by_count":83,"area":"offlinerl"},{"id":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83,"area":"offlinerl"},{"id":"2310.08566","title":"Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining","created":"2023-10-12","cited_by_count":83,"area":"offlinerl"},{"id":"2110.08695","title":"Towards Instance-Optimal Offline Reinforcement Learning with Pessimism","created":"2021-10-17","cited_by_count":78,"area":"offlinerl"},{"id":"2405.00254","title":"RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation","created":"2024-04-30","cited_by_count":74,"area":"alignment"},{"id":"2405.19320","title":"Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF","created":"2024-05-29","cited_by_count":73,"area":"alignment"},{"id":"2305.18438","title":"Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism","created":"2023-05-29","cited_by_count":69,"area":"alignment"},{"id":"2203.05804","title":"Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism","created":"2022-03-11","cited_by_count":65,"area":"offlinerl"},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57,"area":"alignment"},{"id":"2205.15512","title":"Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game","created":"2022-05-31","cited_by_count":55,"area":"offlinerl"},{"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":"2402.07314","title":"Online Iterative Reinforcement Learning from Human Feedback with General Preference Model","created":"2024-02-11","cited_by_count":52,"area":"alignment"},{"id":"2106.06630","title":"Corruption-Robust Offline Reinforcement Learning","created":"2021-06-11","cited_by_count":51,"area":"offlinerl"},{"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":"2205.11790","title":"Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning","created":"2022-05-24","cited_by_count":50,"area":"offlinerl"},{"id":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50,"area":"alignment"},{"id":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45,"area":null},{"id":"2106.06431","title":"Offline Reinforcement Learning as Anti-Exploration","created":"2021-06-11","cited_by_count":44,"area":"offlinerl"},{"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":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42,"area":null},{"id":"2211.04974","title":"Leveraging Offline Data in Online Reinforcement Learning","created":"2022-11-09","cited_by_count":42,"area":"offlinerl"},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2309.12696","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning","created":"2023-09-22","cited_by_count":37,"area":"offlinerl"},{"id":"2110.09796","title":"Offline Reinforcement Learning with Value-based Episodic Memory","created":"2021-10-19","cited_by_count":36,"area":"offlinerl"},{"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":"2403.05171","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation","created":"2024-03-08","cited_by_count":33,"area":"alignment"},{"id":"2110.14000","title":"Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning","created":"2021-10-26","cited_by_count":32,"area":"offlinerl"},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32,"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":"2302.11048","title":"Adversarial Model for Offline Reinforcement Learning","created":"2023-02-21","cited_by_count":31,"area":"offlinerl"},{"id":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31,"area":"offlinerl"},{"id":"2206.00159","title":"Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus","created":"2022-06-01","cited_by_count":30,"area":"offlinerl"},{"id":"2311.12996","title":"RLIF: Interactive Imitation Learning as Reinforcement Learning","created":"2023-11-21","cited_by_count":30,"area":"offlinerl"},{"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":"2201.03522","title":"When is Offline Two-Player Zero-Sum Markov Game Solvable?","created":"2022-01-10","cited_by_count":28,"area":null},{"id":"2310.05333","title":"DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning","created":"2023-10-09","cited_by_count":28,"area":"diffusion"},{"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":"2403.01857","title":"Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences","created":"2024-03-04","cited_by_count":27,"area":"alignment"},{"id":"2508.08170","title":"ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction","created":"2025-08-11","cited_by_count":27,"area":"diffusion"},{"id":"2106.03207","title":"Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage","created":"2021-06-06","cited_by_count":26,"area":"offlinerl"},{"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":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2111.13807","title":"Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization","created":"2021-11-27","cited_by_count":25,"area":"offlinerl"},{"id":"2404.18909","title":"Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty","created":"2024-04-29","cited_by_count":25,"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":"2211.12612","title":"Transfer Learning for Contextual Multi-armed Bandits","created":"2022-11-22","cited_by_count":24,"area":null},{"id":"2310.04413","title":"Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-10-06","cited_by_count":24,"area":"offlinerl"},{"id":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24,"area":"offlinerl"},{"id":"2206.00695","title":"Know Your Boundaries: The Necessity of Explicit Behavioral Cloning in Offline RL","created":"2022-06-01","cited_by_count":21,"area":"offlinerl"},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2212.04607","title":"Confidence-Conditioned Value Functions for Offline Reinforcement Learning","created":"2022-12-08","cited_by_count":20,"area":"offlinerl"},{"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":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2207.10148","title":"Learning Deformable Object Manipulation from Expert Demonstrations","created":"2022-07-20","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":"2302.02571","title":"Offline Learning in Markov Games with General Function Approximation","created":"2023-02-06","cited_by_count":18,"area":"offlinerl"},{"id":"2305.12944","title":"Offline Primal-Dual Reinforcement Learning for Linear MDPs","created":"2023-05-22","cited_by_count":17,"area":"offlinerl"},{"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":"2206.03383","title":"On the Role of Discount Factor in Offline Reinforcement Learning","created":"2022-06-07","cited_by_count":16,"area":"offlinerl"},{"id":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2210.03802","title":"Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization","created":"2022-10-07","cited_by_count":16,"area":"offlinerl"},{"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":"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":"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":"2304.07278","title":"Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning","created":"2023-04-14","cited_by_count":15,"area":"offlinerl"},{"id":"2306.07923","title":"Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits","created":"2023-06-13","cited_by_count":15,"area":"offlinerl"},{"id":"2309.15771","title":"Importance-Weighted Offline Learning Done Right","created":"2023-09-27","cited_by_count":15,"area":"offlinerl"},{"id":"2105.06029","title":"Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings","created":"2021-05-13","cited_by_count":14,"area":"offlinerl"},{"id":"2403.12946","title":"Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes","created":"2024-03-19","cited_by_count":14,"area":"offlinerl"},{"id":"2405.20984","title":"Bayesian Design Principles for Offline-to-Online Reinforcement Learning","created":"2024-05-31","cited_by_count":14,"area":"offlinerl"},{"id":"2206.00165","title":"Byzantine-Robust Online and Offline Distributed Reinforcement Learning","created":"2022-06-01","cited_by_count":13,"area":null},{"id":"2206.00177","title":"On Gap-dependent Bounds for Offline Reinforcement Learning","created":"2022-06-01","cited_by_count":13,"area":"offlinerl"},{"id":"2206.06426","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","created":"2022-06-13","cited_by_count":13,"area":"offlinerl"},{"id":"2211.01052","title":"Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints","created":"2022-11-02","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":"2302.00662","title":"Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders","created":"2023-02-01","cited_by_count":13,"area":"offlinerl"},{"id":"2302.03319","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2307.12975","title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems","created":"2023-07-24","cited_by_count":13,"area":"alignment"},{"id":"2310.18687","title":"Unsupervised Behavior Extraction via Random Intent Priors","created":"2023-10-28","cited_by_count":13,"area":"offlinerl"}],"next_cursor":"100"}