{"total":114,"rows":[{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363,"area":null},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174,"area":null},{"id":"2305.09836","title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","created":"2023-05-16","cited_by_count":126,"area":"offlinerl"},{"id":"2405.16158","title":"Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control","created":"2024-05-25","cited_by_count":108,"area":"deeprl"},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"id":"2208.07860","title":"A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning","created":"2022-08-16","cited_by_count":83,"area":"wm"},{"id":"2302.13425","title":"A Survey on Uncertainty Quantification Methods for Deep Learning","created":"2023-02-26","cited_by_count":81,"area":null},{"id":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76,"area":"deeprl"},{"id":"2311.02198","title":"Imitation Bootstrapped Reinforcement Learning","created":"2023-11-03","cited_by_count":64,"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":"2403.00514","title":"Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning","created":"2024-03-01","cited_by_count":50,"area":"deeprl"},{"id":"2301.07784","title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","created":"2023-01-18","cited_by_count":48,"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":"2306.10711","title":"PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning","created":"2023-06-19","cited_by_count":42,"area":null},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"2402.12479","title":"In value-based deep reinforcement learning, a pruned network is a good network","created":"2024-02-19","cited_by_count":39,"area":"deeprl"},{"id":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38,"area":"deeprl"},{"id":"2304.10466","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","created":"2023-04-20","cited_by_count":36,"area":null},{"id":"2304.09834","title":"Learning and Adapting Agile Locomotion Skills by Transferring Experience","created":"2023-04-19","cited_by_count":33,"area":null},{"id":"2404.14735","title":"Rank2Reward: Learning Shaped Reward Functions from Passive Video","created":"2024-04-23","cited_by_count":32,"area":"deeprl"},{"id":"2304.04150","title":"RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning","created":"2023-04-09","cited_by_count":30,"area":null},{"id":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"area":"deeprl"},{"id":"2401.11963","title":"Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms","created":"2024-01-22","cited_by_count":26,"area":"deeprl"},{"id":"2310.17634","title":"Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion","created":"2023-10-26","cited_by_count":24,"area":null},{"id":"2212.09902","title":"Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance","created":"2022-12-19","cited_by_count":23,"area":null},{"id":"2211.11092","title":"Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size","created":"2022-11-20","cited_by_count":21,"area":"offlinerl"},{"id":"2502.07523","title":"Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization","created":"2025-02-11","cited_by_count":19,"area":"deeprl"},{"id":"2403.05996","title":"Dissecting Deep RL with High Update Ratios: Combatting Value Divergence","created":"2024-03-09","cited_by_count":17,"area":"deeprl"},{"id":"2502.02705","title":"Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning","created":"2025-02-04","cited_by_count":17,"area":null},{"id":"2509.25174","title":"XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning","created":"2025-09-29","cited_by_count":17,"area":"deeprl"},{"id":"2410.08896","title":"MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL","created":"2024-10-11","cited_by_count":16,"area":"deeprl"},{"id":"2410.09163","title":"Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models","created":"2024-10-11","cited_by_count":16,"area":"deeprl"},{"id":"2507.06892","title":"Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2306.00656","title":"Normalization Enhances Generalization in Visual Reinforcement Learning","created":"2023-06-01","cited_by_count":13,"area":null},{"id":"2305.18443","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","created":"2023-05-29","cited_by_count":12,"area":null},{"id":"2310.15017","title":"Mind the Model, Not the Agent: The Primacy Bias in Model-based RL","created":"2023-10-23","cited_by_count":9,"area":"wm"},{"id":"2310.13396","title":"RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup","created":"2023-10-20","cited_by_count":8,"area":null},{"id":"2311.01059","title":"Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2503.08375","title":"Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion","created":"2025-03-11","cited_by_count":8,"area":"deeprl"},{"id":"2405.13136","title":"Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs","created":"2024-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2501.08669","title":"SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning","created":"2025-01-15","cited_by_count":7,"area":"deeprl"},{"id":"2303.06164","title":"Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning","created":"2023-03-10","cited_by_count":6,"area":null},{"id":"2310.19527","title":"On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics","created":"2023-10-30","cited_by_count":6,"area":null},{"id":"2403.02107","title":"Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning","created":"2024-03-04","cited_by_count":6,"area":"deeprl"},{"id":"2408.04054","title":"PLANRL: A Motion Planning and Imitation Learning Framework to Bootstrap Reinforcement Learning","created":"2024-08-07","cited_by_count":6,"area":"offlinerl"},{"id":"2410.08540","title":"Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning","created":"2024-10-11","cited_by_count":6,"area":null},{"id":"2506.13672","title":"The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning","created":"2025-06-16","cited_by_count":6,"area":"deeprl"},{"id":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"deeprl"},{"id":"2603.15759","title":"Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation","created":"2026-03-16","cited_by_count":6,"area":"wm"},{"id":"2405.19080","title":"OMPO: A Unified Framework for RL under Policy and Dynamics Shifts","created":"2024-05-29","cited_by_count":5,"area":"deeprl"},{"id":"2502.07937","title":"Active Advantage-Aligned Online Reinforcement Learning with Offline Data","created":"2025-02-11","cited_by_count":5,"area":"offlinerl"},{"id":"2604.04539","title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","created":"2026-04-06","cited_by_count":5,"area":"deeprl"},{"id":"2407.06584","title":"HiLMa-Res: A General Hierarchical Framework via Residual RL for Combining Quadrupedal Locomotion and Manipulation","created":"2024-07-09","cited_by_count":4,"area":"deeprl"},{"id":"2408.11048","title":"RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands","created":"2024-08-20","cited_by_count":4,"area":"offlinerl"},{"id":"2503.19333","title":"E-PINNs: Epistemic Physics-Informed Neural Networks","created":"2025-03-25","cited_by_count":4,"area":null},{"id":"2205.09117","title":"Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks","created":"2022-05-18","cited_by_count":3,"area":null},{"id":"2210.03649","title":"How to Enable Uncertainty Estimation in Proximal Policy Optimization","created":"2022-10-07","cited_by_count":3,"area":null},{"id":"2503.05905","title":"Performance Comparisons of Reinforcement Learning Algorithms for Sequential Experimental Design","created":"2025-03-07","cited_by_count":3,"area":"deeprl"},{"id":"2503.08322","title":"Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programs","created":"2025-03-11","cited_by_count":3,"area":"deeprl"},{"id":"2510.25529","title":"Off-policy Reinforcement Learning with Model-based Exploration Augmentation","created":"2025-10-29","cited_by_count":3,"area":"deeprl"},{"id":"2512.13359","title":"Fast Policy Learning for 6-DOF Position Control of Underwater Vehicles","created":"2025-12-15","cited_by_count":3,"area":null},{"id":"2401.02914","title":"A unified uncertainty-aware exploration: Combining epistemic and aleatory uncertainty","created":"2024-01-05","cited_by_count":2,"area":"deeprl"},{"id":"2407.04864","title":"Augmented Bayesian Policy Search","created":"2024-07-05","cited_by_count":2,"area":"deeprl"},{"id":"2409.07606","title":"The Role of Deep Learning Regularizations on Actors in Offline RL","created":"2024-09-11","cited_by_count":2,"area":"offlinerl"},{"id":"2410.10438","title":"Reinforcement Learning For Quadrupedal Locomotion: Current Advancements And Future Perspectives","created":"2024-10-14","cited_by_count":2,"area":"deeprl"},{"id":"2410.14957","title":"Offline-to-online Reinforcement Learning for Image-based Grasping with Scarce Demonstrations","created":"2024-10-19","cited_by_count":2,"area":"offlinerl"},{"id":"2503.15481","title":"Learning to Play Piano in the Real World","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2506.13892","title":"Scaling Algorithm Distillation for Continuous Control with Mamba","created":"2025-06-16","cited_by_count":2,"area":"ssm"},{"id":"2602.11800","title":"Temporal Difference Learning with Constrained Initial Representations","created":"2026-02-12","cited_by_count":2,"area":"deeprl"},{"id":"2209.07171","title":"Learning to Exploit Elastic Actuators for Quadruped Locomotion","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2312.05787","title":"Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2401.05251","title":"ReACT: Reinforcement Learning for Controller Parametrization using B-Spline Geometries","created":"2024-01-10","cited_by_count":1,"area":"deeprl"},{"id":"2403.07704","title":"Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning","created":"2024-03-12","cited_by_count":1,"area":"deeprl"},{"id":"2404.00651","title":"Learning Off-policy with Model-based Intrinsic Motivation For Active Online Exploration","created":"2024-03-31","cited_by_count":1,"area":"deeprl"},{"id":"2404.16159","title":"AFU: Actor-Free critic Updates in off-policy RL for continuous control","created":"2024-04-24","cited_by_count":1,"area":"deeprl"},{"id":"2405.10576","title":"An Efficient Learning Control Framework With Sim-to-Real for String-Type Artificial Muscle-Driven Robotic Systems","created":"2024-05-17","cited_by_count":1,"area":"deeprl"},{"id":"2405.14629","title":"Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of Experiences","created":"2024-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2405.16739","title":"Oracle-Efficient Reinforcement Learning for Max Value Ensembles","created":"2024-05-27","cited_by_count":1,"area":"deeprl"},{"id":"2506.03758","title":"Scaling CrossQ with Weight Normalization","created":"2025-06-04","cited_by_count":1,"area":"deeprl"},{"id":"2507.11486","title":"Exploring the robustness of TractOracle methods in RL-based tractography","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.07746","title":"A Tutorial: An Intuitive Explanation of Offline Reinforcement Learning Theory","created":"2025-08-11","cited_by_count":1,"area":"offlinerl"},{"id":"2509.04069","title":"Solving Robotics Tasks with Prior Demonstration via Exploration-Efficient Deep Reinforcement Learning","created":"2025-09-04","cited_by_count":1,"area":"deeprl"},{"id":"2510.01105","title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2512.15439","title":"Double Horizon Model-Based Policy Optimization","created":"2025-12-17","cited_by_count":1,"area":"deeprl"},{"id":"2601.21363","title":"Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control","created":"2026-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2602.05619","title":"Mode-Dependent Rectification for Stable PPO Training","created":"2026-02-05","cited_by_count":1,"area":"deeprl"},{"id":"2603.05066","title":"Reward-Conditioned Reinforcement Learning","created":"2026-03-05","cited_by_count":1,"area":"alignment"},{"id":"2605.05863","title":"SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data","created":"2026-05-07","cited_by_count":1,"area":"deeprl"},{"id":"2605.11711","title":"Debiased Model-based Representations for Sample-efficient Continuous Control","created":"2026-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2605.21214","title":"Behavior-Consistent Deep Reinforcement Learning","created":"2026-05-20","cited_by_count":1,"area":"deeprl"},{"id":"2606.05888","title":"Retry Policy Gradients in Continuous Action Spaces","created":"2026-06-04","cited_by_count":1,"area":"deeprl"},{"id":"2301.11168","title":"Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2310.14009","title":"One is More: Diverse Perspectives within a Single Network for Efficient DRL","created":"2023-10-21","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":"2403.01014","title":"A Case for Validation Buffer in Pessimistic Actor-Critic","created":"2024-03-01","cited_by_count":0,"area":"deeprl"},{"id":"2404.06188","title":"Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning","created":"2024-04-09","cited_by_count":0,"area":"offlinerl"},{"id":"2405.08252","title":"Smart Sampling: Self-Attention and Bootstrapping for Improved Ensembled Q-Learning","created":"2024-05-14","cited_by_count":0,"area":null},{"id":"2406.17490","title":"BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO","created":"2024-06-25","cited_by_count":0,"area":"deeprl"},{"id":"2408.02022","title":"Scenario-based Thermal Management Parametrization Through Deep Reinforcement Learning","created":"2024-08-04","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}