{"total":108,"rows":[{"id":"2502.02538","title":"Flow Q-Learning","created":"2025-02-04","cited_by_count":184,"area":"diffusion"},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"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":"2502.02316","title":"DIME:Diffusion-Based Maximum Entropy Reinforcement Learning","created":"2025-02-04","cited_by_count":58,"area":"diffusion"},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2504.11054","title":"Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models","created":"2025-04-15","cited_by_count":56,"area":"deeprl"},{"id":"2503.14858","title":"1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities","created":"2025-03-19","cited_by_count":45,"area":"deeprl"},{"id":"2505.22642","title":"FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control","created":"2025-05-28","cited_by_count":44,"area":"deeprl"},{"id":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38,"area":"deeprl"},{"id":"2502.11612","title":"Maximum Entropy Reinforcement Learning with Diffusion Policy","created":"2025-02-17","cited_by_count":34,"area":"diffusion"},{"id":"2411.04832","title":"Plasticity Loss in Deep Reinforcement Learning: A Survey","created":"2024-11-07","cited_by_count":24,"area":"deeprl"},{"id":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2506.15544","title":"Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning","created":"2025-06-18","cited_by_count":23,"area":"deeprl"},{"id":"2509.06863","title":"floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL","created":"2025-09-08","cited_by_count":22,"area":"diffusion"},{"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":"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":"2503.03660","title":"Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns","created":"2025-03-05","cited_by_count":16,"area":"deeprl"},{"id":"2512.01996","title":"Learning Sim-to-Real Humanoid Locomotion in 15 Minutes","created":"2025-12-01","cited_by_count":16,"area":"deeprl"},{"id":"2502.04327","title":"Value-Based Deep RL Scales Predictably","created":"2025-02-06","cited_by_count":15,"area":"deeprl"},{"id":"2505.24061","title":"Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning","created":"2025-05-29","cited_by_count":14,"area":"deeprl"},{"id":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2506.17204","title":"Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":11,"area":"deeprl"},{"id":"2605.25477","title":"EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models","created":"2026-05-25","cited_by_count":11,"area":"vla"},{"id":"2510.07730","title":"DEAS: DEtached value learning with Action Sequence for Scalable Offline RL","created":"2025-10-09","cited_by_count":10,"area":"offlinerl"},{"id":"2410.05026","title":"Active Fine-Tuning of Multi-Task Policies","created":"2024-10-07","cited_by_count":9,"area":"offlinerl"},{"id":"2507.02712","title":"A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control","created":"2025-07-03","cited_by_count":9,"area":"deeprl"},{"id":"2602.01439","title":"TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse","created":"2026-02-01","cited_by_count":9,"area":"deeprl"},{"id":"2503.05126","title":"Multi-Task Reinforcement Learning Enables Parameter Scaling","created":"2025-03-07","cited_by_count":8,"area":"deeprl"},{"id":"2509.18648","title":"SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer","created":"2025-09-23","cited_by_count":8,"area":"deeprl"},{"id":"2505.15345","title":"Hadamax Encoding: Elevating Performance in Model-Free Atari","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2507.11019","title":"Relative Entropy Pathwise Policy Optimization","created":"2025-07-15","cited_by_count":7,"area":"deeprl"},{"id":"2608.09853","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","created":"2026-08-10","cited_by_count":7,"area":"alignment"},{"id":"2503.01437","title":"Eau De $Q$-Network: Adaptive Distillation of Neural Networks in Deep Reinforcement Learning","created":"2025-03-03","cited_by_count":6,"area":"deeprl"},{"id":"2503.05546","title":"Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learning","created":"2025-03-07","cited_by_count":6,"area":"deeprl"},{"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":"2508.14881","title":"Compute-Optimal Scaling for Value-Based Deep RL","created":"2025-08-20","cited_by_count":6,"area":"deeprl"},{"id":"2510.06288","title":"BuilderBench: The Building Blocks of Intelligent Agents","created":"2025-10-07","cited_by_count":6,"area":"agents"},{"id":"2503.10626","title":"NIL: No-data Imitation Learning by Leveraging Pre-trained Video Diffusion Models","created":"2025-03-13","cited_by_count":5,"area":"diffusion"},{"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":"2606.22630","title":"Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching","created":"2026-06-21","cited_by_count":5,"area":"diffusion"},{"id":"2503.19037","title":"Evolutionary Policy Optimization","created":"2025-03-24","cited_by_count":4,"area":"deeprl"},{"id":"2504.09906","title":"Plasticity-Aware Mixture of Experts for Learning Under QoE Shifts in Adaptive Video Streaming","created":"2025-04-14","cited_by_count":4,"area":"moe"},{"id":"2505.17749","title":"Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning","created":"2025-05-23","cited_by_count":4,"area":"deeprl"},{"id":"2506.04398","title":"Bridging the Performance Gap Between Target-Free and Target-Based Reinforcement Learning","created":"2025-06-04","cited_by_count":4,"area":"deeprl"},{"id":"2510.21995","title":"Is Temporal Difference Learning the Gold Standard for Stitching in RL?","created":"2025-10-24","cited_by_count":4,"area":"deeprl"},{"id":"2602.05051","title":"ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation","created":"2026-02-04","cited_by_count":4,"area":"offlinerl"},{"id":"2509.23183","title":"ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse","created":"2025-09-27","cited_by_count":3,"area":"lr"},{"id":"2510.25529","title":"Off-policy Reinforcement Learning with Model-based Exploration Augmentation","created":"2025-10-29","cited_by_count":3,"area":"deeprl"},{"id":"2512.14202","title":"Understanding and Improving Hyperbolic Deep Reinforcement Learning","created":"2025-12-16","cited_by_count":3,"area":"deeprl"},{"id":"2512.15036","title":"Spectral Representation-based Reinforcement Learning","created":"2025-12-17","cited_by_count":3,"area":"deeprl"},{"id":"2602.14351","title":"WIMLE: Uncertainty-Aware World Models with IMLE for Sample-Efficient Continuous Control","created":"2026-02-15","cited_by_count":3,"area":"wm"},{"id":"2602.20220","title":"What Matters for Simulation to Online Reinforcement Learning on Real Robots","created":"2026-02-23","cited_by_count":3,"area":"deeprl"},{"id":"2603.06009","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2603.27450","title":"FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies","created":"2026-03-29","cited_by_count":3,"area":"diffusion"},{"id":"2605.30749","title":"FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance","created":"2026-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2406.08440","title":"Adaptive Swarm Mesh Refinement using Deep Reinforcement Learning with Local Rewards","created":"2024-06-12","cited_by_count":2,"area":"deeprl"},{"id":"2504.17490","title":"Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning","created":"2025-04-24","cited_by_count":2,"area":"deeprl"},{"id":"2505.06182","title":"Apple: Toward General Active Perception via Reinforcement Learning","created":"2025-05-09","cited_by_count":2,"area":"deeprl"},{"id":"2505.22772","title":"Calibrated Value-Aware Model Learning with Probabilistic Environment Models","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2507.14736","title":"Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning","created":"2025-07-19","cited_by_count":2,"area":"deeprl"},{"id":"2508.06871","title":"Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning","created":"2025-08-09","cited_by_count":2,"area":"deeprl"},{"id":"2510.02590","title":"Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning","created":"2025-10-02","cited_by_count":2,"area":"deeprl"},{"id":"2601.06133","title":"A Review of Online Diffusion Policy RL Algorithms for Scalable Robotic Control","created":"2026-01-05","cited_by_count":2,"area":"diffusion"},{"id":"2602.11800","title":"Temporal Difference Learning with Constrained Initial Representations","created":"2026-02-12","cited_by_count":2,"area":"deeprl"},{"id":"2602.21203","title":"Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics","created":"2026-02-24","cited_by_count":2,"area":"deeprl"},{"id":"2603.04333","title":"What Does Flow Matching Bring To TD Learning?","created":"2026-03-04","cited_by_count":2,"area":"diffusion"},{"id":"2604.09159","title":"Truncated Rectified Flow Policy for Reinforcement Learning with One-Step Sampling","created":"2026-04-10","cited_by_count":2,"area":"diffusion"},{"id":"2605.31273","title":"Survival Reinforcement Learning: Toward Scalable Self-Supervised RL","created":"2026-05-29","cited_by_count":2,"area":"deeprl"},{"id":"2609.18207","title":"Reinforcement Learning for Real-Time Vision-Language-Action Policies","created":"2026-09-16","cited_by_count":2,"area":"vla"},{"id":"2406.09079","title":"Hadamard Representation: Scaffolding Performance Across Model-free RL","created":"2024-06-13","cited_by_count":1,"area":"deeprl"},{"id":"2502.11949","title":"Massively Scaling Explicit Policy-conditioned Value Functions","created":"2025-02-17","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":"2506.10167","title":"Wasserstein Barycenter Soft Actor-Critic","created":"2025-06-11","cited_by_count":1,"area":"deeprl"},{"id":"2507.08718","title":"On the Effect of Regularization in Policy Mirror Descent","created":"2025-07-11","cited_by_count":1,"area":"deeprl"},{"id":"2508.01329","title":"Is Exploration or Optimization the Problem for Deep Reinforcement Learning?","created":"2025-08-02","cited_by_count":1,"area":"deeprl"},{"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":"2510.12096","title":"Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning","created":"2025-10-14","cited_by_count":1,"area":"deeprl"},{"id":"2601.23075","title":"RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning","created":"2026-01-30","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":"2603.12612","title":"FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control","created":"2026-03-13","cited_by_count":1,"area":"deeprl"},{"id":"2605.08733","title":"Generative Actor-Critic with Soft Bridge Policies","created":"2026-05-09","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":"2606.20411","title":"Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning","created":"2026-06-18","cited_by_count":1,"area":"deeprl"},{"id":"2606.29820","title":"Dual-Flow Reinforcement Learning with State-Aware Exploration","created":"2026-06-29","cited_by_count":1,"area":"deeprl"},{"id":"2509.22964","title":"Functional Critics Are Essential for Actor-Critic: From Off-Policy Stability to Efficient Exploration","created":"2025-09-26","cited_by_count":0,"area":"deeprl"},{"id":"2604.18978","title":"Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning","created":"2026-04-21","cited_by_count":0,"area":"deeprl"},{"id":"2604.20381","title":"Distributional Value Estimation Without Target Networks for Robust Quality-Diversity","created":"2026-04-22","cited_by_count":0,"area":"deeprl"},{"id":"2605.10236","title":"When Does Non-Uniform Replay Matter in Reinforcement Learning?","created":"2026-05-11","cited_by_count":0,"area":"deeprl"},{"id":"2605.14026","title":"R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2605.21282","title":"Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent","created":"2026-05-20","cited_by_count":0,"area":"deeprl"},{"id":"2606.20210","title":"Augmenting Game AI with Deep Reinforcement Learning","created":"2026-06-18","cited_by_count":0,"area":"deeprl"},{"id":"2606.31291","title":"Deep Reinforcement Learning for Spacecraft Attitude Control During Atmospheric Re-Entry","created":"2026-06-30","cited_by_count":0,"area":"deeprl"},{"id":"2607.01880","title":"Learning the Supports for Categorical Critic in Reinforcement Learning","created":"2026-07-02","cited_by_count":0,"area":"deeprl"},{"id":"2607.23930","title":"Bridging Reinforcement Learning and Optimal Control via Feasible Action Mapping","created":"2026-07-27","cited_by_count":0,"area":"deeprl"},{"id":"2608.02034","title":"Upper-Expectile Multi-Step Q-Learning for Off-Policy Reinforcement Learning","created":"2026-08-03","cited_by_count":0,"area":"deeprl"},{"id":"2608.07086","title":"Beyond Isolation: Unlocking Reinforcement Learning Component Synergy for Sample-Efficient Continuous Control","created":"2026-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2608.07180","title":"Momba: Network Modernization Improves Multi-Objective Reinforcement Learning","created":"2026-08-07","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}