{"total":218,"rows":[{"id":"2405.21046","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","created":"2024-05-31","cited_by_count":106,"area":"alignment"},{"id":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104,"area":"synth"},{"id":"2204.08967","title":"When Is Partially Observable Reinforcement Learning Not Scary?","created":"2022-04-19","cited_by_count":100,"area":null},{"id":"2306.14111","title":"Is RLHF More Difficult than Standard RL?","created":"2023-06-25","cited_by_count":96,"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":"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":"2509.06941","title":"Outcome-based Exploration for LLM Reasoning","created":"2025-09-08","cited_by_count":83,"area":"lr"},{"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":"2202.04690","title":"Smoothed Online Learning is as Easy as Statistical Learning","created":"2022-02-09","cited_by_count":52,"area":null},{"id":"2201.11206","title":"Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes","created":"2022-01-26","cited_by_count":49,"area":null},{"id":"2204.03991","title":"The Complexity of Markov Equilibrium in Stochastic Games","created":"2022-04-08","cited_by_count":49,"area":null},{"id":"2207.05738","title":"PAC Reinforcement Learning for Predictive State Representations","created":"2022-07-12","cited_by_count":43,"area":null},{"id":"2211.04974","title":"Leveraging Offline Data in Online Reinforcement Learning","created":"2022-11-09","cited_by_count":42,"area":"offlinerl"},{"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":"2206.13063","title":"On the Complexity of Adversarial Decision Making","created":"2022-06-27","cited_by_count":33,"area":null},{"id":"2207.02575","title":"Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design","created":"2022-07-06","cited_by_count":33,"area":null},{"id":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"area":null},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2206.07659","title":"Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2209.15634","title":"A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning","created":"2022-09-30","cited_by_count":31,"area":null},{"id":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31,"area":"offlinerl"},{"id":"2206.03446","title":"Learning in Observable POMDPs, without Computationally Intractable Oracles","created":"2022-06-07","cited_by_count":30,"area":null},{"id":"2211.07484","title":"Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression","created":"2022-11-14","cited_by_count":30,"area":null},{"id":"2301.08215","title":"Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient","created":"2023-01-19","cited_by_count":30,"area":null},{"id":"2302.06606","title":"Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation","created":"2023-02-13","cited_by_count":30,"area":null},{"id":"2408.14511","title":"Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods","created":"2024-08-25","cited_by_count":29,"area":"lr"},{"id":"2302.03673","title":"Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation","created":"2023-02-07","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":"2206.04282","title":"Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2404.03578","title":"Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms","created":"2024-04-04","cited_by_count":26,"area":"deeprl"},{"id":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","cited_by_count":24,"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":"2202.08549","title":"Oracle-Efficient Online Learning for Beyond Worst-Case Adversaries","created":"2022-02-17","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":"2205.13924","title":"Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits","created":"2022-05-27","cited_by_count":19,"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":"2207.05849","title":"Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces","created":"2022-07-12","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":"2306.09210","title":"Optimal Exploration for Model-Based RL in Nonlinear Systems","created":"2023-06-15","cited_by_count":18,"area":null},{"id":"2310.00806","title":"Bayesian Design Principles for Frequentist Sequential Learning","created":"2023-10-01","cited_by_count":18,"area":null},{"id":"2405.19883","title":"From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems","created":"2024-05-30","cited_by_count":17,"area":null},{"id":"2502.10581","title":"Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective","created":"2025-02-14","cited_by_count":17,"area":"lr"},{"id":"2207.02357","title":"Instance-optimal PAC Algorithms for Contextual Bandits","created":"2022-07-05","cited_by_count":16,"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":"2307.03997","title":"Efficient Model-Free Exploration in Low-Rank MDPs","created":"2023-07-08","cited_by_count":16,"area":null},{"id":"2406.12125","title":"Efficient Sequential Decision Making with Large Language Models","created":"2024-06-17","cited_by_count":16,"area":null},{"id":"2210.16976","title":"Representation Learning for General-sum Low-rank Markov Games","created":"2022-10-30","cited_by_count":15,"area":null},{"id":"2212.08765","title":"Latent Variable Representation for Reinforcement Learning","created":"2022-12-17","cited_by_count":15,"area":null},{"id":"2301.11518","title":"Online Learning in Stackelberg Games with an Omniscient Follower","created":"2023-01-27","cited_by_count":15,"area":null},{"id":"2302.01333","title":"Lower Bounds for Learning in Revealing POMDPs","created":"2023-02-02","cited_by_count":15,"area":null},{"id":"2502.20548","title":"$Q\\sharp$: Provably Optimal Distributional RL for LLM Post-Training","created":"2025-02-27","cited_by_count":15,"area":"lr"},{"id":"2202.10997","title":"Minimax Regret for Partial Monitoring: Infinite Outcomes and Rustichini's Regret","created":"2022-02-22","cited_by_count":14,"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":"2306.00212","title":"Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2311.15238","title":"A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation","created":"2023-11-26","cited_by_count":14,"area":null},{"id":"2212.13835","title":"Representation Learning in Deep RL via Discrete Information Bottleneck","created":"2022-12-28","cited_by_count":13,"area":null},{"id":"2402.14987","title":"On the Performance of Empirical Risk Minimization with Smoothed Data","created":"2024-02-22","cited_by_count":13,"area":null},{"id":"2502.12465","title":"Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification","created":"2025-02-18","cited_by_count":13,"area":"offlinerl"},{"id":"2210.02087","title":"Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration and Planning","created":"2022-10-05","cited_by_count":12,"area":null},{"id":"2302.03683","title":"Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2402.08991","title":"Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption","created":"2024-02-14","cited_by_count":12,"area":"deeprl"},{"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":"2506.05295","title":"Sample Complexity and Representation Ability of Test-time Scaling Paradigms","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2207.11126","title":"Optimism in Face of a Context: Regret Guarantees for Stochastic Contextual MDP","created":"2022-07-22","cited_by_count":11,"area":null},{"id":"2211.14250","title":"Model-Free Reinforcement Learning with the Decision-Estimation Coefficient","created":"2022-11-25","cited_by_count":11,"area":null},{"id":"2302.08631","title":"Practical Contextual Bandits with Feedback Graphs","created":"2023-02-17","cited_by_count":11,"area":null},{"id":"2408.08994","title":"Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds","created":"2024-08-16","cited_by_count":11,"area":"deeprl"},{"id":"2203.08248","title":"Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling","created":"2022-03-15","cited_by_count":10,"area":null},{"id":"2205.11470","title":"Exploiting the Curvature of Feasible Sets for Faster Projection-Free Online Learning","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2405.17061","title":"Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation","created":"2024-05-27","cited_by_count":10,"area":"deeprl"},{"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":"2211.14932","title":"Eluder-based Regret for Stochastic Contextual MDPs","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2302.10796","title":"Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret","created":"2023-02-21","cited_by_count":9,"area":null},{"id":"2303.01464","title":"Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation","created":"2023-03-02","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":"2402.05724","title":"Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL","created":"2024-02-08","cited_by_count":9,"area":"deeprl"},{"id":"2409.16197","title":"Second Order Bounds for Contextual Bandits with Function Approximation","created":"2024-09-24","cited_by_count":9,"area":null},{"id":"2410.12713","title":"How Does Variance Shape the Regret in Contextual Bandits?","created":"2024-10-16","cited_by_count":9,"area":null},{"id":"2405.17796","title":"Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2409.12799","title":"The Central Role of the Loss Function in Reinforcement Learning","created":"2024-09-19","cited_by_count":8,"area":"deeprl"},{"id":"2506.12721","title":"Strategic Scaling of Test-Time Compute: A Bandit Learning Approach","created":"2025-06-15","cited_by_count":8,"area":"lr"},{"id":"2512.16911","title":"Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning","created":"2025-12-18","cited_by_count":8,"area":"offlinerl"},{"id":"2206.02326","title":"Asymptotic Instance-Optimal Algorithms for Interactive Decision Making","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2207.08342","title":"A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation","created":"2022-07-18","cited_by_count":7,"area":null},{"id":"2302.06025","title":"Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits","created":"2023-02-12","cited_by_count":7,"area":null},{"id":"2303.04845","title":"Smoothed Analysis of Sequential Probability Assignment","created":"2023-03-08","cited_by_count":7,"area":null},{"id":"2307.06877","title":"The complexity of non-stationary reinforcement learning","created":"2023-07-13","cited_by_count":7,"area":null},{"id":"2402.15411","title":"Optimistic Information Directed Sampling","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2405.20165","title":"Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation","created":"2024-05-30","cited_by_count":7,"area":"deeprl"},{"id":"2406.01386","title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond","created":"2024-06-03","cited_by_count":7,"area":"deeprl"},{"id":"2410.07533","title":"Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification","created":"2024-10-10","cited_by_count":7,"area":null},{"id":"2505.20268","title":"Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits","created":"2025-05-26","cited_by_count":7,"area":"deeprl"},{"id":"2510.15464","title":"Learning to Answer from Correct Demonstrations","created":"2025-10-17","cited_by_count":7,"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":"2306.00861","title":"Non-stationary Reinforcement Learning under General Function Approximation","created":"2023-06-01","cited_by_count":6,"area":null},{"id":"2306.09554","title":"Low-Switching Policy Gradient with Exploration via Online Sensitivity Sampling","created":"2023-06-15","cited_by_count":6,"area":null}],"next_cursor":"100"}