{"total":77,"rows":[{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"id":"2206.08332","title":"BYOL-Explore: Exploration by Bootstrapped Prediction","created":"2022-06-16","cited_by_count":73,"area":null},{"id":"2310.19668","title":"DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization","created":"2023-10-30","cited_by_count":47,"area":null},{"id":"2103.01312","title":"UCB Momentum Q-learning: Correcting the bias without forgetting","created":"2021-03-01","cited_by_count":46,"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":"2202.06385","title":"Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost","created":"2022-02-13","cited_by_count":32,"area":null},{"id":"2306.12371","title":"Optimistic Active Exploration of Dynamical Systems","created":"2023-06-21","cited_by_count":32,"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":"2110.06394","title":"Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation","created":"2021-10-12","cited_by_count":29,"area":null},{"id":"2206.10770","title":"On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL","created":"2022-06-21","cited_by_count":27,"area":null},{"id":"2207.08645","title":"Active Exploration for Inverse Reinforcement Learning","created":"2022-07-18","cited_by_count":27,"area":"offlinerl"},{"id":"2201.11861","title":"The Challenges of Exploration for Offline Reinforcement Learning","created":"2022-01-27","cited_by_count":26,"area":"offlinerl"},{"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":"2210.16913","title":"Revisiting Simple Regret: Fast Rates for Returning a Good Arm","created":"2022-10-30","cited_by_count":25,"area":null},{"id":"2206.02678","title":"Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path","created":"2022-06-06","cited_by_count":22,"area":null},{"id":"2304.12966","title":"Towards Theoretical Understanding of Inverse Reinforcement Learning","created":"2023-04-25","cited_by_count":21,"area":"offlinerl"},{"id":"2305.15284","title":"Replicable Reinforcement Learning","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2102.06875","title":"Improved Corruption Robust Algorithms for Episodic Reinforcement Learning","created":"2021-02-13","cited_by_count":20,"area":null},{"id":"2110.09771","title":"On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game","created":"2021-10-19","cited_by_count":20,"area":null},{"id":"2206.00121","title":"Near-Optimal Collaborative Learning in Bandits","created":"2022-05-31","cited_by_count":18,"area":null},{"id":"2203.09251","title":"Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs","created":"2022-03-17","cited_by_count":17,"area":null},{"id":"2207.05852","title":"Optimistic PAC Reinforcement Learning: the Instance-Dependent View","created":"2022-07-12","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":"2306.06563","title":"Provably Efficient Adversarial Imitation Learning with Unknown Transitions","created":"2023-06-11","cited_by_count":16,"area":"offlinerl"},{"id":"2402.14528","title":"ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization","created":"2024-02-22","cited_by_count":16,"area":"deeprl"},{"id":"2110.03743","title":"Reinforcement Learning in Reward-Mixing MDPs","created":"2021-10-07","cited_by_count":15,"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":"2304.08944","title":"Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning","created":"2023-04-18","cited_by_count":15,"area":null},{"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":"2110.03244","title":"Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver","created":"2021-10-07","cited_by_count":14,"area":null},{"id":"2303.10859","title":"Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs","created":"2023-03-20","cited_by_count":14,"area":null},{"id":"2210.00701","title":"Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2310.00817","title":"Learning to Make Adherence-Aware Advice","created":"2023-10-01","cited_by_count":13,"area":null},{"id":"2405.17108","title":"Finding good policies in average-reward Markov Decision Processes without prior knowledge","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"2202.06545","title":"Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization","created":"2022-02-14","cited_by_count":12,"area":null},{"id":"2209.14414","title":"Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2302.06064","title":"Provably Safe Reinforcement Learning with Step-wise Violation Constraints","created":"2023-02-13","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":"2108.05439","title":"Gap-Dependent Unsupervised Exploration for Reinforcement Learning","created":"2021-08-11","cited_by_count":10,"area":null},{"id":"2206.14057","title":"Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL","created":"2022-06-28","cited_by_count":10,"area":null},{"id":"2310.06793","title":"Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning","created":"2023-10-10","cited_by_count":10,"area":null},{"id":"2306.13601","title":"Active Coverage for PAC Reinforcement Learning","created":"2023-06-23","cited_by_count":8,"area":null},{"id":"2411.03810","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","created":"2024-11-06","cited_by_count":8,"area":"deeprl"},{"id":"2303.10165","title":"Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs","created":"2023-03-17","cited_by_count":7,"area":null},{"id":"2311.05638","title":"Towards Instance-Optimality in Online PAC Reinforcement Learning","created":"2023-10-31","cited_by_count":7,"area":null},{"id":"2406.01389","title":"RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2502.02516","title":"Adaptive Exploration for Multi-Reward Multi-Policy Evaluation","created":"2025-02-04","cited_by_count":6,"area":null},{"id":"2210.02594","title":"Reward-Mixing MDPs with a Few Latent Contexts are Learnable","created":"2022-10-05","cited_by_count":5,"area":"alignment"},{"id":"2406.02282","title":"Test-Time Regret Minimization in Meta Reinforcement Learning","created":"2024-06-04","cited_by_count":5,"area":"deeprl"},{"id":"2406.03812","title":"How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach","created":"2024-06-06","cited_by_count":5,"area":"offlinerl"},{"id":"2406.16255","title":"Uncertainty-Aware Reward-Free Exploration with General Function Approximation","created":"2024-06-24","cited_by_count":5,"area":"deeprl"},{"id":"2111.12045","title":"Adaptive Multi-Goal Exploration","created":"2021-11-23","cited_by_count":4,"area":null},{"id":"2401.08961","title":"Cascading Reinforcement Learning","created":"2024-01-17","cited_by_count":4,"area":"deeprl"},{"id":"2402.01111","title":"Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints","created":"2024-02-02","cited_by_count":4,"area":"deeprl"},{"id":"2411.15046","title":"On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning","created":"2024-11-22","cited_by_count":4,"area":"offlinerl"},{"id":"2506.09508","title":"Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design","created":"2025-06-11","cited_by_count":3,"area":"alignment"},{"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":"2202.07995","title":"Branching Reinforcement Learning","created":"2022-02-16","cited_by_count":2,"area":null},{"id":"2503.00810","title":"Minimax Optimal Reinforcement Learning with Quasi-Optimism","created":"2025-03-02","cited_by_count":2,"area":"deeprl"},{"id":"2510.09325","title":"Rate optimal learning of equilibria from data","created":"2025-10-10","cited_by_count":2,"area":"offlinerl"},{"id":"2604.24532","title":"A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning","created":"2026-04-27","cited_by_count":2,"area":"deeprl"},{"id":"2106.07203","title":"Online Sub-Sampling for Reinforcement Learning with General Function Approximation","created":"2021-06-14","cited_by_count":1,"area":null},{"id":"2409.15963","title":"Provably Efficient Exploration in Inverse Constrained Reinforcement Learning","created":"2024-09-24","cited_by_count":1,"area":"deeprl"},{"id":"2512.10042","title":"SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation","created":"2025-12-10","cited_by_count":1,"area":"deeprl"},{"id":"2601.11890","title":"From Relative Entropy to Minimax: A Unified Framework for Coverage in MDPs","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2602.16363","title":"Improved Bounds for Reward-Agnostic and Reward-Free Exploration","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2602.22810","title":"Multi-agent imitation learning with function approximation: Linear Markov games and beyond","created":"2026-02-26","cited_by_count":1,"area":"offlinerl"},{"id":"2302.03789","title":"Layered State Discovery for Incremental Autonomous Exploration","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2306.03832","title":"Stochastic Principal-Agent Problems: Efficient Computation and Learning","created":"2023-06-06","cited_by_count":0,"area":null},{"id":"2505.13188","title":"When a Reinforcement Learning Agent Encounters Unknown Unknowns","created":"2025-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2602.01453","title":"The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.20404","title":"$\\kappa$-Explorer: A Unified Framework for Active Model Estimation in MDPs","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.01309","title":"PAC Guarantees for Reinforcement Learning: Sample Complexity, Coverage, and Structure","created":"2026-03-01","cited_by_count":0,"area":"deeprl"},{"id":"2605.04979","title":"On-line Learning in Tree MDPs by Treating Policies as Bandit Arms","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.23182","title":"Pure Exploration for a Good Policy in Reinforcement Learning with Bandit Feedback","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2607.01897","title":"Rank-Then-Act: Reward-Free Control from Frame-Order Progress","created":"2026-07-02","cited_by_count":0,"area":"alignment"},{"id":"2607.29294","title":"Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification","created":"2026-07-31","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}