{"total":96,"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":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114,"area":null},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104,"area":null},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"id":"2302.13425","title":"A Survey on Uncertainty Quantification Methods for Deep Learning","created":"2023-02-26","cited_by_count":81,"area":null},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2509.19301","title":"Residual Off-Policy RL for Finetuning Behavior Cloning Policies","created":"2025-09-23","cited_by_count":55,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"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":"2202.00821","title":"Optimizing Sequential Experimental Design with Deep Reinforcement Learning","created":"2022-02-02","cited_by_count":46,"area":null},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2208.01160","title":"Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot","created":"2022-08-01","cited_by_count":38,"area":null},{"id":"2304.10466","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","created":"2023-04-20","cited_by_count":36,"area":null},{"id":"2303.01488","title":"Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning","created":"2023-03-02","cited_by_count":34,"area":null},{"id":"2507.07986","title":"EXPO: Stable Reinforcement Learning with Expressive Policies","created":"2025-07-10","cited_by_count":34,"area":null},{"id":"2102.08159","title":"RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents","created":"2021-02-16","cited_by_count":31,"area":null},{"id":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2310.07418","title":"Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages","created":"2023-10-11","cited_by_count":28,"area":null},{"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":"2103.06469","title":"Generalizable Episodic Memory for Deep Reinforcement Learning","created":"2021-03-11","cited_by_count":23,"area":null},{"id":"2112.10504","title":"Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic","created":"2021-12-16","cited_by_count":23,"area":null},{"id":"2410.01432","title":"Adaptive teachers for amortized samplers","created":"2024-10-02","cited_by_count":23,"area":null},{"id":"2409.20568","title":"Continuously Improving Mobile Manipulation with Autonomous Real-World RL","created":"2024-09-30","cited_by_count":22,"area":null},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2110.03375","title":"Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning","created":"2021-10-07","cited_by_count":18,"area":null},{"id":"2202.07013","title":"Robust Policy Learning over Multiple Uncertainty Sets","created":"2022-02-14","cited_by_count":18,"area":null},{"id":"2207.12141","title":"Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy","created":"2022-07-25","cited_by_count":17,"area":null},{"id":"2306.09466","title":"Simplified Temporal Consistency Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"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":"2202.05404","title":"Regularized Q-learning","created":"2022-02-11","cited_by_count":16,"area":null},{"id":"2210.15479","title":"Low-Rank Modular Reinforcement Learning via Muscle Synergy","created":"2022-10-26","cited_by_count":16,"area":null},{"id":"2303.02618","title":"Ensemble Reinforcement Learning: A Survey","created":"2023-03-05","cited_by_count":16,"area":null},{"id":"2209.07670","title":"Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks","created":"2022-09-16","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":"2404.12638","title":"Learning to Cut via Hierarchical Sequence/Set Model for Efficient Mixed-Integer Programming","created":"2024-04-19","cited_by_count":12,"area":null},{"id":"2203.11526","title":"Action Candidate Driven Clipped Double Q-learning for Discrete and Continuous Action Tasks","created":"2022-03-22","cited_by_count":9,"area":null},{"id":"2306.11918","title":"Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2201.13357","title":"DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning","created":"2022-01-31","cited_by_count":8,"area":null},{"id":"2205.12381","title":"First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization","created":"2022-05-24","cited_by_count":8,"area":null},{"id":"2205.14557","title":"Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning","created":"2022-05-29","cited_by_count":8,"area":null},{"id":"2306.07124","title":"Diverse Projection Ensembles for Distributional Reinforcement Learning","created":"2023-06-12","cited_by_count":8,"area":null},{"id":"2306.10430","title":"Variational Sequential Optimal Experimental Design using Reinforcement Learning","created":"2023-06-17","cited_by_count":8,"area":null},{"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":"2401.03137","title":"SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning","created":"2024-01-06","cited_by_count":8,"area":null},{"id":"2506.07259","title":"ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition","created":"2025-06-08","cited_by_count":8,"area":null},{"id":"2111.09159","title":"Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance","created":"2021-11-17","cited_by_count":7,"area":null},{"id":"2310.17786","title":"Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates","created":"2023-10-26","cited_by_count":7,"area":null},{"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":"2305.18435","title":"Statistically Efficient Bayesian Sequential Experiment Design via Reinforcement Learning with Cross-Entropy Estimators","created":"2023-05-29","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":"2410.08540","title":"Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning","created":"2024-10-11","cited_by_count":6,"area":null},{"id":"2106.08918","title":"Towards Automatic Actor-Critic Solutions to Continuous Control","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2109.10552","title":"MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2303.02378","title":"Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control","created":"2023-03-04","cited_by_count":5,"area":null},{"id":"2310.11138","title":"Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control","created":"2023-10-17","cited_by_count":5,"area":null},{"id":"2109.14419","title":"On the Estimation Bias in Double Q-Learning","created":"2021-09-29","cited_by_count":4,"area":null},{"id":"2311.18393","title":"Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control","created":"2023-11-30","cited_by_count":4,"area":null},{"id":"2111.02787","title":"Balanced Q-learning: Combining the Influence of Optimistic and Pessimistic Targets","created":"2021-11-03","cited_by_count":3,"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":"2312.15965","title":"Efficient Reinforcement Learning via Decoupling Exploration and Utilization","created":"2023-12-26","cited_by_count":3,"area":null},{"id":"2409.15317","title":"Shared Autonomy with IDA: Interventional Diffusion Assistance","created":"2024-09-05","cited_by_count":3,"area":null},{"id":"2205.12770","title":"An Experimental Comparison Between Temporal Difference and Residual Gradient with Neural Network Approximation","created":"2022-05-25","cited_by_count":2,"area":null},{"id":"2206.10027","title":"DNA: Proximal Policy Optimization with a Dual Network Architecture","created":"2022-06-20","cited_by_count":2,"area":null},{"id":"2302.09875","title":"Backstepping Temporal Difference Learning","created":"2023-02-20","cited_by_count":2,"area":null},{"id":"2306.16750","title":"Eigensubspace of Temporal-Difference Dynamics and How It Improves Value Approximation in Reinforcement Learning","created":"2023-06-29","cited_by_count":2,"area":null},{"id":"2309.12560","title":"Machine Learning Meets Advanced Robotic Manipulation","created":"2023-09-22","cited_by_count":2,"area":null},{"id":"2404.09715","title":"Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2412.02029","title":"Learning Ensembles of Vision-based Safety Control Filters","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2412.07477","title":"Progressive-Resolution Policy Distillation: Leveraging Coarse-Resolution Simulations for Time-Efficient Fine-Resolution Policy Learning","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2606.10614","title":"Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2110.09712","title":"Balancing Value Underestimation and Overestimation with Realistic Actor-Critic","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2203.05961","title":"Random Ensemble Reinforcement Learning for Traffic Signal Control","created":"2022-03-10","cited_by_count":1,"area":null},{"id":"2210.02585","title":"Query The Agent: Improving sample efficiency through epistemic uncertainty estimation","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2304.09087","title":"MDDL: A Framework for Reinforcement Learning-based Position Allocation in Multi-Channel Feed","created":"2023-04-17","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":"2506.18627","title":"Multi-Agent Reinforcement Learning for Inverse Design in Photonic Integrated Circuits","created":"2025-06-23","cited_by_count":1,"area":null},{"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":"2510.10709","title":"Missing Data Multiple Imputation for Tabular Q-Learning in Online RL","created":"2025-10-12","cited_by_count":1,"area":null},{"id":"2605.03065","title":"OGPO: Sample Efficient Full-Finetuning of Generative Control Policies","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2205.10739","title":"Offline Policy Comparison with Confidence: Benchmarks and Baselines","created":"2022-05-22","cited_by_count":0,"area":null},{"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":"2305.11017","title":"Deep Metric Tensor Regularized Policy Gradient","created":"2023-05-18","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":"2403.05732","title":"Conservative DDPG -- Pessimistic RL without Ensemble","created":"2024-03-08","cited_by_count":0,"area":null},{"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":"2503.05970","title":"Partially Decentralized Multi-Agent Q-Learning via Digital Cousins for Wireless Networks","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2503.11964","title":"Entropy-regularized Gradient Estimators for Approximate Bayesian Inference","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2506.01568","title":"Trajectory First: A Curriculum for Discovering Diverse Policies","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2605.05791","title":"Fitted Q-Iteration with Continuous Actions and Adaptive Data: Smoothed Coverage and Minimax Rates","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2609.32752","title":"Action Shaping: Policies Absorb What They Can Express","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}