{"total":76,"rows":[{"id":"2502.02538","title":"Flow Q-Learning","created":"2025-02-04","cited_by_count":184,"area":"diffusion"},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"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":"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":"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":"2510.01656","title":"Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning","created":"2025-10-02","cited_by_count":10,"area":"lr"},{"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":"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":"2602.08040","title":"FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff","created":"2026-02-08","cited_by_count":7,"area":null},{"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":"2508.14881","title":"Compute-Optimal Scaling for Value-Based Deep RL","created":"2025-08-20","cited_by_count":6,"area":"deeprl"},{"id":"2509.01765","title":"Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control","created":"2025-09-01","cited_by_count":5,"area":"deeprl"},{"id":"2602.19373","title":"Stable Deep Reinforcement Learning via Isotropic Gaussian Representations","created":"2026-02-22","cited_by_count":5,"area":"deeprl"},{"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":"2503.19037","title":"Evolutionary Policy Optimization","created":"2025-03-24","cited_by_count":4,"area":"deeprl"},{"id":"2601.07524","title":"Stagewise Reinforcement Learning and the Geometry of the Regret Landscape","created":"2026-01-12","cited_by_count":4,"area":"deeprl"},{"id":"2602.10539","title":"What Makes Value Learning Efficient in Residual Reinforcement Learning?","created":"2026-02-11","cited_by_count":4,"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":"2512.14202","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":"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":"2606.01672","title":"RDA: Reward Design Agent for Reinforcement Learning","created":"2026-06-01","cited_by_count":3,"area":"agents"},{"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":"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":"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":"2604.01913","title":"The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning","created":"2026-04-02","cited_by_count":2,"area":"deeprl"},{"id":"2605.31273","title":"Survival Reinforcement Learning: Toward Scalable Self-Supervised RL","created":"2026-05-29","cited_by_count":2,"area":"deeprl"},{"id":"2606.06746","title":"Performance Variation in Deep Reinforcement Learning","created":"2026-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2502.11949","title":"Massively Scaling Explicit Policy-conditioned Value Functions","created":"2025-02-17","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":"2508.03194","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":"2601.21363","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":"2601.23075","title":"RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning","created":"2026-01-30","cited_by_count":1,"area":"deeprl"},{"id":"2603.01694","title":"MVR: Multi-view Video Reward Shaping for Reinforcement Learning","created":"2026-03-02","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":"2609.16683","title":"Weave: Learning Whole-Body Dexterous Loco-Manipulation from Human-Object Interactions","created":"2026-09-15","cited_by_count":1,"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":"2511.18987","title":"Dynamic Mixture of Experts Against Severe Distribution Shifts","created":"2025-11-24","cited_by_count":0,"area":"moe"},{"id":"2602.17632","title":"SMAC: Score-Matched Actor-Critics for Robust Offline-to-Online Transfer","created":"2026-02-19","cited_by_count":0,"area":"offlinerl"},{"id":"2602.21680","title":"Hierarchical Lead Critic based Multi-Agent Reinforcement Learning","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.08588","title":"Towards Batch-to-Streaming Deep Reinforcement Learning for Continuous Control","created":"2026-03-09","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":"2604.19677","title":"Learning Hybrid-Control Policies for High-Precision In-Contact Manipulation Under Uncertainty","created":"2026-04-21","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":"2605.11473","title":"TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.22463","title":"Reinforcement learning for ion shuttling on trapped-ion quantum computers","created":"2026-05-21","cited_by_count":0,"area":"deeprl"},{"id":"2606.03382","title":"Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2607.24320","title":"Continual-RL for Generalization in Autonomous Racing on the RoboRacer Platform","created":"2026-07-27","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"},{"id":"2608.07335","title":"A Progressive Design Study of Visual Encoders and Value Estimation for Replay-Free Parallelized Q-Learning","created":"2026-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2608.07870","title":"V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control","created":"2026-08-08","cited_by_count":0,"area":"deeprl"},{"id":"2608.26571","title":"Arrive and Survive: Scaling Safe Goal-Conditioned Policy Learning from One-Bit Failure Signals","created":"2026-08-27","cited_by_count":0,"area":"deeprl"},{"id":"2609.06958","title":"Mind the Phase: Effective Rank and Representation Health in Legged Locomotion","created":"2026-09-07","cited_by_count":0,"area":"deeprl"},{"id":"2609.32819","title":"Rank Collapse Is Recoverable, Growing $|Q|$ Is Not: Out-of-Sample Early Warning for Value Divergence in High-UTD Soft Actor-Critic","created":"2026-09-26","cited_by_count":0,"area":"deeprl"},{"id":"2609.36238","title":"ChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2610.10857","title":"Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.13354","title":"AlphaNIST: Emergent Assembly Skills from Binary Task Rewards","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.20009","title":"Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}