{"total":92,"rows":[{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"id":"2103.10897","title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","created":"2021-03-19","cited_by_count":178,"area":null},{"id":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164,"area":"offlinerl"},{"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":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"id":"2102.07035","title":"Model-free Representation Learning and Exploration in Low-rank MDPs","created":"2021-02-14","cited_by_count":82,"area":null},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69,"area":"alignment"},{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","cited_by_count":62,"area":null},{"id":"2103.12923","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","created":"2021-03-24","cited_by_count":53,"area":null},{"id":"2107.08346","title":"Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses","created":"2021-07-18","cited_by_count":52,"area":null},{"id":"2202.00063","title":"Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach","created":"2022-01-31","cited_by_count":51,"area":null},{"id":"2210.05805","title":"Exploration via Elliptical Episodic Bonuses","created":"2022-10-11","cited_by_count":51,"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":"2110.03580","title":"A Model Selection Approach for Corruption Robust Reinforcement Learning","created":"2021-10-07","cited_by_count":45,"area":null},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","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":"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":"2102.05800","title":"Robust Policy Gradient against Strong Data Corruption","created":"2021-02-11","cited_by_count":30,"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":"2106.02847","title":"Navigating to the Best Policy in Markov Decision Processes","created":"2021-06-05","cited_by_count":29,"area":null},{"id":"2305.08841","title":"A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes","created":"2023-05-15","cited_by_count":29,"area":null},{"id":"2206.02346","title":"Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs","created":"2022-06-06","cited_by_count":27,"area":null},{"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":"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":"2402.10342","title":"Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization","created":"2024-02-15","cited_by_count":25,"area":"alignment"},{"id":"2011.04019","title":"Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient","created":"2020-11-08","cited_by_count":24,"area":"offlinerl"},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2108.05533","title":"Efficient Local Planning with Linear Function Approximation","created":"2021-08-12","cited_by_count":23,"area":null},{"id":"2201.01251","title":"Multi-Stage Episodic Control for Strategic Exploration in Text Games","created":"2022-01-04","cited_by_count":22,"area":null},{"id":"2106.00669","title":"Discovering Diverse Nearly Optimal Policies with Successor Features","created":"2021-06-01","cited_by_count":20,"area":null},{"id":"2106.02193","title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2302.09456","title":"Distributional Offline Policy Evaluation with Predictive Error Guarantees","created":"2023-02-19","cited_by_count":20,"area":"diffusion"},{"id":"2306.03236","title":"A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2301.12942","title":"Refined Regret for Adversarial MDPs with Linear Function Approximation","created":"2023-01-30","cited_by_count":19,"area":null},{"id":"2105.14016","title":"Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model","created":"2021-05-28","cited_by_count":18,"area":null},{"id":"2111.14629","title":"Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions","created":"2021-11-29","cited_by_count":17,"area":"offlinerl"},{"id":"2203.09251","title":"Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs","created":"2022-03-17","cited_by_count":17,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2301.13087","title":"Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation","created":"2023-01-30","cited_by_count":17,"area":null},{"id":"2302.09408","title":"Best of Both Worlds Policy Optimization","created":"2023-02-18","cited_by_count":17,"area":null},{"id":"2110.08984","title":"Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs","created":"2021-10-18","cited_by_count":16,"area":null},{"id":"2204.09787","title":"Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency","created":"2022-04-20","cited_by_count":16,"area":null},{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2107.07410","title":"PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration","created":"2021-07-15","cited_by_count":14,"area":null},{"id":"2308.14642","title":"Rate-Optimal Policy Optimization for Linear Markov Decision Processes","created":"2023-08-28","cited_by_count":14,"area":null},{"id":"2403.11574","title":"Offline Multitask Representation Learning for Reinforcement Learning","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2103.11559","title":"Provably Correct Optimization and Exploration with Non-linear Policies","created":"2021-03-22","cited_by_count":13,"area":null},{"id":"2106.11519","title":"Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2303.04386","title":"Policy Mirror Descent Inherently Explores Action Space","created":"2023-03-08","cited_by_count":13,"area":null},{"id":"2305.11032","title":"Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL","created":"2023-05-18","cited_by_count":13,"area":null},{"id":"2310.11550","title":"Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback","created":"2023-10-17","cited_by_count":13,"area":null},{"id":"2106.08414","title":"On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control","created":"2021-06-15","cited_by_count":12,"area":null},{"id":"2108.09767","title":"A Boosting Approach to Reinforcement Learning","created":"2021-08-22","cited_by_count":12,"area":null},{"id":"2311.08384","title":"Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees","created":"2023-11-14","cited_by_count":11,"area":"offlinerl"},{"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":"2211.10282","title":"Exploring through Random Curiosity with General Value Functions","created":"2022-11-18","cited_by_count":10,"area":null},{"id":"2301.12579","title":"Sample Efficient Deep Reinforcement Learning via Local Planning","created":"2023-01-29","cited_by_count":10,"area":null},{"id":"2410.23022","title":"Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback","created":"2024-10-30","cited_by_count":10,"area":"agents"},{"id":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"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":"2109.06362","title":"Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods","created":"2021-09-13","cited_by_count":7,"area":null},{"id":"2306.10694","title":"On the Model-Misspecification in Reinforcement Learning","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2405.03064","title":"RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation","created":"2024-05-05","cited_by_count":7,"area":"deeprl"},{"id":"2302.04376","title":"Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning","created":"2023-02-08","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},{"id":"2407.07631","title":"Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning","created":"2024-07-10","cited_by_count":6,"area":"offlinerl"},{"id":"2407.13755","title":"Random Latent Exploration for Deep Reinforcement Learning","created":"2024-07-18","cited_by_count":6,"area":"deeprl"},{"id":"2601.16403","title":"Towards a Theoretical Understanding to the Generalization of RLHF","created":"2026-01-23","cited_by_count":6,"area":"alignment"},{"id":"2111.00185","title":"Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings","created":"2021-10-30","cited_by_count":5,"area":null},{"id":"2206.00796","title":"Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2510.14129","title":"Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL","created":"2025-10-15","cited_by_count":5,"area":"deeprl"},{"id":"2302.09703","title":"Reinforcement Learning with Function Approximation: From Linear to Nonlinear","created":"2023-02-20","cited_by_count":4,"area":null},{"id":"2407.12185","title":"Satisficing Exploration for Deep Reinforcement Learning","created":"2024-07-16","cited_by_count":4,"area":"deeprl"},{"id":"2305.02605","title":"Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policy","created":"2023-05-04","cited_by_count":3,"area":null},{"id":"2407.15083","title":"Rocket Landing Control with Random Annealing Jump Start Reinforcement Learning","created":"2024-07-21","cited_by_count":3,"area":"deeprl"},{"id":"2510.21060","title":"On the Sample Complexity of Differentially Private Policy Optimization","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2512.06244","title":"Auto-exploration for online reinforcement learning","created":"2025-12-06","cited_by_count":3,"area":"deeprl"},{"id":"2301.10330","title":"Off-Policy Evaluation for Action-Dependent Non-Stationary Environments","created":"2023-01-24","cited_by_count":2,"area":null},{"id":"2308.05471","title":"Provably Efficient Algorithm for Nonstationary Low-Rank MDPs","created":"2023-08-10","cited_by_count":2,"area":null},{"id":"2312.17248","title":"Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity","created":"2023-12-28","cited_by_count":2,"area":"lr"},{"id":"2410.01249","title":"Dual Approximation Policy Optimization","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2106.15503","title":"Curious Explorer: a provable exploration strategy in Policy Learning","created":"2021-06-29","cited_by_count":1,"area":null},{"id":"2211.15205","title":"CIM: Constrained Intrinsic Motivation for Sparse-Reward Continuous Control","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2503.18980","title":"CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning","created":"2025-03-23","cited_by_count":1,"area":"deeprl"},{"id":"2504.02130","title":"Ordering-based Conditions for Global Convergence of Policy Gradient Methods","created":"2025-04-02","cited_by_count":1,"area":"deeprl"},{"id":"2205.13950","title":"Non-Markovian policies occupancy measures","created":"2022-05-27","cited_by_count":0,"area":null},{"id":"2301.03142","title":"Exploration in Model-based Reinforcement Learning with Randomized Reward","created":"2023-01-09","cited_by_count":0,"area":null},{"id":"2510.05703","title":"Provably Convergent Primal-Dual DPO for Constrained LLM Alignment","created":"2025-10-07","cited_by_count":0,"area":"alignment"},{"id":"2510.11933","title":"Efficient Restarts in Non-Stationary Model-Free Reinforcement Learning","created":"2025-10-13","cited_by_count":0,"area":"deeprl"},{"id":"2510.22420","title":"A Novel Multi-Timescale Stability-Preserving Hierarchical Reinforcement Learning Controller Framework for Adaptive Control in High-Dimensional Dynamical Systems","created":"2025-10-25","cited_by_count":0,"area":"deeprl"},{"id":"2603.12087","title":"Cross-Domain Policy Optimization via Bellman Consistency and Hybrid Critics","created":"2026-03-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.20592","title":"ReversedQ: Opportunities for Faster Q-Learning in Episodic Online Reinforcement Learning","created":"2026-05-20","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}