{"total":116,"rows":[{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364,"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":"2106.04895","title":"Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning","created":"2021-06-09","cited_by_count":158,"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":"2205.11140","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","created":"2022-05-23","cited_by_count":81,"area":null},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80,"area":null},{"id":"2207.04630","title":"On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence","created":"2022-07-11","cited_by_count":50,"area":"lr"},{"id":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","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":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","cited_by_count":44,"area":"offlinerl"},{"id":"2107.14702","title":"Towards General Function Approximation in Zero-Sum Markov Games","created":"2021-07-30","cited_by_count":43,"area":null},{"id":"2212.05949","title":"Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes","created":"2022-12-12","cited_by_count":33,"area":null},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"id":"2208.10904","title":"A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning","created":"2022-08-23","cited_by_count":31,"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":"2302.09205","title":"Approximate Thompson Sampling via Epistemic Neural Networks","created":"2023-02-18","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":"2111.11485","title":"A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning","created":"2021-11-22","cited_by_count":24,"area":null},{"id":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2310.19848","title":"Efficient Exploration in Continuous-time Model-based Reinforcement Learning","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2105.14989","title":"Representation Learning Beyond Linear Prediction Functions","created":"2021-05-31","cited_by_count":21,"area":null},{"id":"2112.10264","title":"Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models","created":"2021-12-19","cited_by_count":21,"area":null},{"id":"2104.06970","title":"Understanding the Eluder Dimension","created":"2021-04-14","cited_by_count":19,"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":"2302.01244","title":"Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function","created":"2023-02-02","cited_by_count":19,"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":"2102.12661","title":"Online Learning for Unknown Partially Observable MDPs","created":"2021-02-25","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":"2210.01907","title":"A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games","created":"2022-10-04","cited_by_count":16,"area":null},{"id":"2402.05367","title":"Principled Preferential Bayesian Optimization","created":"2024-02-08","cited_by_count":16,"area":null},{"id":"2110.03743","title":"Reinforcement Learning in Reward-Mixing MDPs","created":"2021-10-07","cited_by_count":15,"area":"alignment"},{"id":"2202.05448","title":"Fast Rates in Pool-Based Batch Active Learning","created":"2022-02-11","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":"2304.08944","title":"Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning","created":"2023-04-18","cited_by_count":15,"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":"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":"2307.02842","title":"Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback","created":"2023-07-06","cited_by_count":14,"area":"alignment"},{"id":"2310.06171","title":"Memory-Consistent Neural Networks for Imitation Learning","created":"2023-10-09","cited_by_count":14,"area":"offlinerl"},{"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":"2212.13540","title":"Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation","created":"2022-12-27","cited_by_count":13,"area":null},{"id":"2110.15843","title":"Adaptive Discretization in Online Reinforcement Learning","created":"2021-10-29","cited_by_count":12,"area":null},{"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":"2110.04422","title":"Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation","created":"2021-10-09","cited_by_count":11,"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":"2210.15598","title":"Provable Sim-to-real Transfer in Continuous Domain with Partial Observations","created":"2022-10-27","cited_by_count":9,"area":null},{"id":"2211.14932","title":"Eluder-based Regret for Stochastic Contextual MDPs","created":"2022-11-27","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":"2305.11455","title":"Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models","created":"2023-05-19","cited_by_count":8,"area":"agents"},{"id":"2107.02377","title":"A Short Note on the Relationship of Information Gain and Eluder Dimension","created":"2021-07-06","cited_by_count":7,"area":null},{"id":"2108.11563","title":"Adaptive Control of Differentially Private Linear Quadratic Systems","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2206.01162","title":"Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning","created":"2022-06-02","cited_by_count":7,"area":null},{"id":"2310.20007","title":"Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2403.00233","title":"Causal Bandits with General Causal Models and Interventions","created":"2024-03-01","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":"2210.16877","title":"On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning","created":"2022-10-30","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":"2309.12671","title":"How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2411.00610","title":"Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation","created":"2024-11-01","cited_by_count":6,"area":"offlinerl"},{"id":"2501.15910","title":"The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective","created":"2025-01-27","cited_by_count":6,"area":"deeprl"},{"id":"2112.14195","title":"Exponential Family Model-Based Reinforcement Learning via Score Matching","created":"2021-12-28","cited_by_count":5,"area":null},{"id":"2209.07676","title":"Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning","created":"2022-09-16","cited_by_count":5,"area":null},{"id":"2306.08803","title":"Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2311.06639","title":"Data-driven rules for multidimensional reflection problems","created":"2023-11-11","cited_by_count":5,"area":null},{"id":"2401.05193","title":"Experiment Planning with Function Approximation","created":"2024-01-10","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":"2602.23116","title":"Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences","created":"2026-02-26","cited_by_count":5,"area":"alignment"},{"id":"2105.10590","title":"Parallelizing Contextual Bandits","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2301.12038","title":"STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning","created":"2023-01-28","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":"2312.04464","title":"Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation","created":"2023-12-07","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":"2410.23912","title":"RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner","created":"2024-10-31","cited_by_count":4,"area":"lr"},{"id":"2510.13512","title":"Offline and Online KL-Regularized RLHF under Differential Privacy","created":"2025-10-15","cited_by_count":4,"area":"alignment"},{"id":"2303.16998","title":"Does Sparsity Help in Learning Misspecified Linear Bandits?","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2305.08350","title":"Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2605.07049","title":"Towards Differentially Private Reinforcement Learning with General Function Approximation","created":"2026-05-07","cited_by_count":3,"area":"deeprl"},{"id":"2110.03424","title":"Bad-Policy Density: A Measure of Reinforcement Learning Hardness","created":"2021-10-07","cited_by_count":2,"area":null},{"id":"2110.12276","title":"Coarse-Grained Smoothness for RL in Metric Spaces","created":"2021-10-23","cited_by_count":2,"area":null},{"id":"2305.17552","title":"Online Nonstochastic Model-Free Reinforcement Learning","created":"2023-05-27","cited_by_count":2,"area":null},{"id":"2309.02815","title":"Near-continuous time Reinforcement Learning for continuous state-action spaces","created":"2023-09-06","cited_by_count":2,"area":null},{"id":"2403.11175","title":"Prior-dependent analysis of posterior sampling reinforcement learning with function approximation","created":"2024-03-17","cited_by_count":2,"area":"deeprl"},{"id":"2503.00810","title":"Minimax Optimal Reinforcement Learning with Quasi-Optimism","created":"2025-03-02","cited_by_count":2,"area":"deeprl"},{"id":"2603.08287","title":"Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces","created":"2026-03-09","cited_by_count":2,"area":"deeprl"},{"id":"2107.05849","title":"Model Selection for Generic Reinforcement Learning","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2207.02992","title":"Model Selection in Reinforcement Learning with General Function Approximations","created":"2022-07-06","cited_by_count":1,"area":null},{"id":"2208.05363","title":"Learning Two-Player Mixture Markov Games: Kernel Function Approximation and Correlated Equilibrium","created":"2022-08-10","cited_by_count":1,"area":null},{"id":"2310.10818","title":"Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2311.01568","title":"Anytime-Competitive Reinforcement Learning with Policy Prior","created":"2023-11-02","cited_by_count":1,"area":null},{"id":"2405.18793","title":"Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement Learning","created":"2024-05-29","cited_by_count":1,"area":"deeprl"},{"id":"2410.09505","title":"HG2P: Hippocampus-inspired High-reward Graph and Model-Free Q-Gradient Penalty for Path Planning and Motion Control","created":"2024-10-12","cited_by_count":1,"area":"deeprl"},{"id":"2412.20824","title":"Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2503.09309","title":"Steering No-Regret Agents in MFGs under Model Uncertainty","created":"2025-03-12","cited_by_count":1,"area":"deeprl"},{"id":"2505.07101","title":"Constrained Online Decision-Making: A Unified Framework","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2507.06859","title":"Episodic Contextual Bandits with Knapsacks under Conversion Models","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2507.22854","title":"A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model","created":"2025-07-30","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":"2602.10971","title":"A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions","created":"2026-02-11","cited_by_count":1,"area":null}],"next_cursor":"100"}