{"total":73,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662,"area":"offlinerl"},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174,"area":null},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"area":"offlinerl"},{"id":"2010.14500","title":"COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning","created":"2020-10-27","cited_by_count":83,"area":"offlinerl"},{"id":"2112.04716","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","created":"2021-12-09","cited_by_count":66,"area":"offlinerl"},{"id":"2412.07762","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","created":"2024-12-10","cited_by_count":63,"area":"offlinerl"},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"id":"2505.11711","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","created":"2025-05-16","cited_by_count":49,"area":null},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48,"area":"offlinerl"},{"id":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2310.20141","title":"Contrastive Difference Predictive Coding","created":"2023-10-31","cited_by_count":36,"area":null},{"id":"2201.12417","title":"Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error","created":"2022-01-28","cited_by_count":32,"area":null},{"id":"2102.04736","title":"Reverb: A Framework For Experience Replay","created":"2021-02-09","cited_by_count":27,"area":null},{"id":"2310.17966","title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","created":"2023-10-27","cited_by_count":26,"area":"offlinerl"},{"id":"2105.07253","title":"Regret Minimization Experience Replay in Off-Policy Reinforcement Learning","created":"2021-05-15","cited_by_count":25,"area":null},{"id":"2204.05036","title":"Pareto Conditioned Networks","created":"2022-04-11","cited_by_count":25,"area":null},{"id":"2212.04717","title":"On the Sensitivity of Reward Inference to Misspecified Human Models","created":"2022-12-09","cited_by_count":25,"area":null},{"id":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","cited_by_count":24,"area":null},{"id":"2106.04335","title":"Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization","created":"2021-06-08","cited_by_count":23,"area":null},{"id":"2212.04607","title":"Confidence-Conditioned Value Functions for Offline Reinforcement Learning","created":"2022-12-08","cited_by_count":20,"area":"offlinerl"},{"id":"2310.04411","title":"Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL","created":"2023-10-06","cited_by_count":20,"area":"offlinerl"},{"id":"2112.03257","title":"Functional Regularization for Reinforcement Learning via Learned Fourier Features","created":"2021-12-06","cited_by_count":17,"area":null},{"id":"2302.07549","title":"Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications","created":"2023-02-15","cited_by_count":17,"area":"offlinerl"},{"id":"2006.16785","title":"Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning","created":"2020-06-28","cited_by_count":15,"area":"offlinerl"},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2510.07650","title":"Value Flows","created":"2025-10-09","cited_by_count":15,"area":"deeprl"},{"id":"2206.07166","title":"Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning","created":"2022-06-14","cited_by_count":14,"area":"offlinerl"},{"id":"2210.05922","title":"A Unified Framework for Alternating Offline Model Training and Policy Learning","created":"2022-10-12","cited_by_count":14,"area":"offlinerl"},{"id":"2211.01052","title":"Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints","created":"2022-11-02","cited_by_count":13,"area":"offlinerl"},{"id":"2306.03362","title":"Boosting Offline Reinforcement Learning with Action Preference Query","created":"2023-06-06","cited_by_count":12,"area":"offlinerl"},{"id":"2602.03773","title":"Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL","created":"2026-02-03","cited_by_count":12,"area":"lr"},{"id":"2202.09673","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning","created":"2022-02-19","cited_by_count":11,"area":"offlinerl"},{"id":"2102.11327","title":"Uncertainty Estimation Using Riemannian Model Dynamics for Offline Reinforcement Learning","created":"2021-02-22","cited_by_count":10,"area":"offlinerl"},{"id":"2401.08819","title":"Learning from Sparse Offline Datasets via Conservative Density Estimation","created":"2024-01-16","cited_by_count":9,"area":"offlinerl"},{"id":"2411.05614","title":"Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey","created":"2024-11-08","cited_by_count":8,"area":"deeprl"},{"id":"2310.20663","title":"Offline RL with Observation Histories: Analyzing and Improving Sample Complexity","created":"2023-10-31","cited_by_count":7,"area":"offlinerl"},{"id":"2106.14993","title":"Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment","created":"2021-06-28","cited_by_count":6,"area":null},{"id":"2306.05412","title":"Decoupled Prioritized Resampling for Offline RL","created":"2023-06-08","cited_by_count":6,"area":"offlinerl"},{"id":"1910.12154","title":"ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations","created":"2019-10-26","cited_by_count":5,"area":"offlinerl"},{"id":"2112.04123","title":"ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2112.04213","title":"Convergence Results For Q-Learning With Experience Replay","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2306.09805","title":"Mimicking Better by Matching the Approximate Action Distribution","created":"2023-06-16","cited_by_count":5,"area":"offlinerl"},{"id":"2408.12136","title":"Provable Domain Adaptation for Offline Reinforcement Learning with Limited Samples","created":"2024-08-22","cited_by_count":5,"area":"offlinerl"},{"id":"2412.16848","title":"ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning","created":"2024-12-22","cited_by_count":5,"area":"offlinerl"},{"id":"2109.14419","title":"On the Estimation Bias in Double Q-Learning","created":"2021-09-29","cited_by_count":4,"area":null},{"id":"2110.02304","title":"You Only Evaluate Once: a Simple Baseline Algorithm for Offline RL","created":"2021-10-05","cited_by_count":4,"area":"offlinerl"},{"id":"2207.03029","title":"Multi-objective Optimization of Notifications Using Offline Reinforcement Learning","created":"2022-07-07","cited_by_count":4,"area":"offlinerl"},{"id":"2305.13185","title":"Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2107.05217","title":"Cautious Actor-Critic","created":"2021-07-12","cited_by_count":3,"area":null},{"id":"2109.07275","title":"DROMO: Distributionally Robust Offline Model-based Policy Optimization","created":"2021-09-15","cited_by_count":3,"area":"offlinerl"},{"id":"2201.05599","title":"Smart Magnetic Microrobots Learn to Swim with Deep Reinforcement Learning","created":"2022-01-14","cited_by_count":3,"area":null},{"id":"2401.16452","title":"Context-Former: Stitching via Latent Conditioned Sequence Modeling","created":"2024-01-29","cited_by_count":3,"area":"offlinerl"},{"id":"2407.03995","title":"ROER: Regularized Optimal Experience Replay","created":"2024-07-04","cited_by_count":3,"area":"deeprl"},{"id":"2106.08774","title":"Analysis and Optimisation of Bellman Residual Errors with Neural Function Approximation","created":"2021-06-16","cited_by_count":2,"area":null},{"id":"2205.09869","title":"Transformer with Memory Replay","created":"2022-05-19","cited_by_count":2,"area":null},{"id":"2210.10469","title":"Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation","created":"2022-10-19","cited_by_count":2,"area":"offlinerl"},{"id":"2410.11338","title":"DIAR: Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation","created":"2024-10-15","cited_by_count":2,"area":"diffusion"},{"id":"2507.17107","title":"Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models","created":"2025-07-23","cited_by_count":2,"area":"alignment"},{"id":"2603.15857","title":"Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2107.07659","title":"Geometric Value Iteration: Dynamic Error-Aware KL Regularization for Reinforcement Learning","created":"2021-07-16","cited_by_count":1,"area":null},{"id":"2111.11758","title":"The Impact of Data Distribution on Q-learning with Function Approximation","created":"2021-11-23","cited_by_count":1,"area":null},{"id":"2203.10445","title":"Smoothing Advantage Learning","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2107.05798","title":"Cautious Policy Programming: Exploiting KL Regularization in Monotonic Policy Improvement for Reinforcement Learning","created":"2021-07-13","cited_by_count":0,"area":null},{"id":"2109.09037","title":"Dual Behavior Regularized Reinforcement Learning","created":"2021-09-19","cited_by_count":0,"area":null},{"id":"2205.07885","title":"Enforcing KL Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2305.12125","title":"A Framework for Provably Stable and Consistent Training of Deep Feedforward Networks","created":"2023-05-20","cited_by_count":0,"area":null},{"id":"2311.18684","title":"Handling Cost and Constraints with Off-Policy Deep Reinforcement Learning","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2402.05963","title":"Frugal Actor-Critic: Sample Efficient Off-Policy Deep Reinforcement Learning Using Unique Experiences","created":"2024-02-05","cited_by_count":0,"area":"deeprl"},{"id":"2504.13484","title":"Monitor and Recover: A Paradigm for Future Research on Distribution Shift in Learning-Enabled Cyber-Physical Systems","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2602.05379","title":"Variance Reduction Based Experience Replay for Policy Optimization","created":"2026-02-05","cited_by_count":0,"area":"deeprl"},{"id":"2609.34593","title":"Deep Weighted Bellman Residual Minimization for $Q^*$ Estimation","created":"2026-09-28","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}