{"total":106,"rows":[{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279,"area":"offlinerl"},{"id":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223,"area":null},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2101.04233","title":"Independent Policy Gradient Methods for Competitive Reinforcement Learning","created":"2021-01-11","cited_by_count":101,"area":null},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"id":"1905.10948","title":"Provably Efficient Imitation Learning from Observation Alone","created":"2019-05-27","cited_by_count":78,"area":"offlinerl"},{"id":"2110.04184","title":"When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?","created":"2021-10-08","cited_by_count":67,"area":null},{"id":"2102.01748","title":"Near-Optimal Offline Reinforcement Learning via Double Variance Reduction","created":"2021-02-02","cited_by_count":56,"area":"offlinerl"},{"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":"2207.07150","title":"Making Linear MDPs Practical via Contrastive Representation Learning","created":"2022-07-14","cited_by_count":52,"area":null},{"id":"2102.04692","title":"Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap","created":"2021-02-09","cited_by_count":49,"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":"2106.03352","title":"The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces","created":"2021-06-07","cited_by_count":48,"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":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45,"area":null},{"id":"2106.02757","title":"Heuristic-Guided Reinforcement Learning","created":"2021-06-05","cited_by_count":42,"area":null},{"id":"2108.02717","title":"Beyond No Regret: Instance-Dependent PAC Reinforcement Learning","created":"2021-08-05","cited_by_count":41,"area":null},{"id":"2101.00494","title":"A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost","created":"2021-01-02","cited_by_count":40,"area":null},{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35,"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":"2101.02055","title":"Geometric Entropic Exploration","created":"2021-01-06","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":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","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":"2105.08024","title":"Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting","created":"2021-05-17","cited_by_count":28,"area":null},{"id":"2203.12922","title":"Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies","created":"2022-03-24","cited_by_count":27,"area":null},{"id":"2102.08492","title":"Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments","created":"2021-02-16","cited_by_count":26,"area":null},{"id":"2105.06022","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","created":"2021-05-13","cited_by_count":26,"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":"2110.10735","title":"Dynamic Bottleneck for Robust Self-Supervised Exploration","created":"2021-10-20","cited_by_count":21,"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":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","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":"2111.00633","title":"Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning","created":"2021-11-01","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":"2302.02252","title":"Reinforcement Learning in Low-Rank MDPs with Density Features","created":"2023-02-04","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":"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":"2504.20997","title":"Toward Efficient Exploration by Large Language Model Agents","created":"2025-04-29","cited_by_count":17,"area":"agents"},{"id":"2106.05335","title":"Online Learning for Stochastic Shortest Path Model via Posterior Sampling","created":"2021-06-09","cited_by_count":16,"area":null},{"id":"2107.08622","title":"Provably Efficient Multi-Task Reinforcement Learning with Model Transfer","created":"2021-07-19","cited_by_count":16,"area":null},{"id":"2102.05214","title":"Task-Optimal Exploration in Linear Dynamical Systems","created":"2021-02-10","cited_by_count":15,"area":null},{"id":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","cited_by_count":15,"area":null},{"id":"2103.12726","title":"Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning","created":"2021-03-23","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":"2102.12769","title":"No-Regret Reinforcement Learning with Heavy-Tailed Rewards","created":"2021-02-25","cited_by_count":14,"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":"2310.00817","title":"Learning to Make Adherence-Aware Advice","created":"2023-10-01","cited_by_count":13,"area":null},{"id":"2103.00360","title":"Exploration and Incentives in Reinforcement Learning","created":"2021-02-28","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":"2306.13601","title":"Active Coverage for PAC Reinforcement Learning","created":"2023-06-23","cited_by_count":8,"area":null},{"id":"2105.06784","title":"Efficient PAC Reinforcement Learning in Regular Decision Processes","created":"2021-05-14","cited_by_count":7,"area":null},{"id":"2206.03569","title":"Overcoming the Long Horizon Barrier for Sample-Efficient Reinforcement Learning with Latent Low-Rank Structure","created":"2022-06-07","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":"2410.08870","title":"Can we hop in general? A discussion of benchmark selection and design using the Hopper environment","created":"2024-10-11","cited_by_count":7,"area":"deeprl"},{"id":"2210.16877","title":"On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning","created":"2022-10-30","cited_by_count":6,"area":null},{"id":"2210.17540","title":"Agent-Time Attention for Sparse Rewards Multi-Agent Reinforcement Learning","created":"2022-10-31","cited_by_count":6,"area":null},{"id":"2403.08955","title":"Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis","created":"2024-03-13","cited_by_count":6,"area":"deeprl"},{"id":"2505.11478","title":"Automatic Reward Shaping from Confounded Offline Data","created":"2025-05-16","cited_by_count":6,"area":"deeprl"},{"id":"2406.02282","title":"Test-Time Regret Minimization in Meta Reinforcement Learning","created":"2024-06-04","cited_by_count":5,"area":"deeprl"},{"id":"2606.00151","title":"Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying","created":"2026-05-29","cited_by_count":5,"area":"deeprl"},{"id":"2208.05633","title":"Best Policy Identification in Linear MDPs","created":"2022-08-11","cited_by_count":4,"area":null},{"id":"2210.05355","title":"Multi-User Reinforcement Learning with Low Rank Rewards","created":"2022-10-11","cited_by_count":4,"area":null},{"id":"2302.11634","title":"Provably Efficient Reinforcement Learning via Surprise Bound","created":"2023-02-22","cited_by_count":4,"area":null},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2305.08359","title":"Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs","created":"2023-05-15","cited_by_count":4,"area":null},{"id":"2306.01243","title":"Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2401.08961","title":"Cascading Reinforcement Learning","created":"2024-01-17","cited_by_count":4,"area":"deeprl"},{"id":"2406.07455","title":"Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis","created":"2024-06-11","cited_by_count":4,"area":"alignment"},{"id":"2407.12185","title":"Satisficing Exploration for Deep Reinforcement Learning","created":"2024-07-16","cited_by_count":4,"area":"deeprl"},{"id":"2408.10381","title":"Efficient Reinforcement Learning in Probabilistic Reward Machines","created":"2024-08-19","cited_by_count":4,"area":"deeprl"},{"id":"2205.15379","title":"Truly Deterministic Policy Optimization","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2210.13075","title":"Hardness in Markov Decision Processes: Theory and Practice","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2405.17628","title":"Tensor Low-rank Approximation of Finite-horizon Value Functions","created":"2024-05-27","cited_by_count":3,"area":"deeprl"},{"id":"2411.10268","title":"Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review","created":"2024-11-15","cited_by_count":3,"area":"offlinerl"},{"id":"2512.15036","title":"Spectral Representation-based Reinforcement Learning","created":"2025-12-17","cited_by_count":3,"area":"deeprl"},{"id":"2106.00589","title":"Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Reinforcement Learning","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2202.07995","title":"Branching Reinforcement Learning","created":"2022-02-16","cited_by_count":2,"area":null},{"id":"2205.09056","title":"Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2407.10207","title":"Learning to Steer Markovian Agents under Model Uncertainty","created":"2024-07-14","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":"2603.03759","title":"Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2210.09255","title":"A Unified Algorithm for Stochastic Path Problems","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2410.02994","title":"Finite-Sample Analysis of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning","created":"2024-10-03","cited_by_count":1,"area":"deeprl"},{"id":"2501.10598","title":"Addressing Finite-Horizon MDPs via Low-Rank Tensor Value Approximation","created":"2025-01-17","cited_by_count":1,"area":"deeprl"},{"id":"2509.17092","title":"On the Limits of Tabular Hardness Metrics for Deep RL: A Study with the Pharos Benchmark","created":"2025-09-21","cited_by_count":1,"area":"deeprl"},{"id":"2602.15076","title":"Near-Optimal Sample Complexity for Online Constrained MDPs","created":"2026-02-16","cited_by_count":1,"area":"deeprl"},{"id":"2109.14811","title":"Surveillance Evasion Through Bayesian Reinforcement Learning","created":"2021-09-30","cited_by_count":0,"area":null},{"id":"2210.13504","title":"Opportunistic Episodic Reinforcement Learning","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2301.04268","title":"Adversarial Online Multi-Task Reinforcement Learning","created":"2023-01-11","cited_by_count":0,"area":null},{"id":"2401.09772","title":"Robotic Test Tube Rearrangement Using Combined Reinforcement Learning and Motion Planning","created":"2024-01-18","cited_by_count":0,"area":"deeprl"},{"id":"2404.00686","title":"Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning","created":"2024-03-31","cited_by_count":0,"area":"deeprl"},{"id":"2404.01131","title":"GOV-REK: Governed Reward Engineering Kernels for Designing Robust Multi-Agent Reinforcement Learning Systems","created":"2024-04-01","cited_by_count":0,"area":"alignment"},{"id":"2501.06376","title":"Robustness in the Face of Partial Identifiability in Reward Learning","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2501.10261","title":"Logarithmic Regret for Nonlinear Control","created":"2025-01-17","cited_by_count":0,"area":null}],"next_cursor":"100"}