{"total":58,"rows":[{"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":"2410.14606","title":"Streaming Deep Reinforcement Learning Finally Works","created":"2024-10-18","cited_by_count":25,"area":"deeprl"},{"id":"2411.04832","title":"Plasticity Loss in Deep Reinforcement Learning: A Survey","created":"2024-11-07","cited_by_count":24,"area":"deeprl"},{"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":"2510.19093","title":"Weight Decay may matter more than muP for Learning Rate Transfer in Practice","created":"2025-10-21","cited_by_count":20,"area":null},{"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":"2410.07994","title":"Neuroplastic Expansion in Deep Reinforcement Learning","created":"2024-10-10","cited_by_count":18,"area":"deeprl"},{"id":"2507.12224","title":"Optimizers Qualitatively Alter Solutions And We Should Leverage This","created":"2025-07-16","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":"2506.03404","title":"The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks","created":"2025-06-03","cited_by_count":13,"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":"2507.20057","title":"What Can Grokking Teach Us About Learning Under Nonstationarity?","created":"2025-07-26","cited_by_count":8,"area":null},{"id":"2508.00212","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","created":"2025-07-31","cited_by_count":6,"area":null},{"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":"2512.14202","title":"Understanding and Improving Hyperbolic Deep Reinforcement Learning","created":"2025-12-16","cited_by_count":3,"area":"deeprl"},{"id":"2606.25971","title":"Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors","created":"2026-06-24","cited_by_count":3,"area":"moe"},{"id":"2412.18790","title":"Torque-Aware Momentum","created":"2024-12-25","cited_by_count":2,"area":null},{"id":"2504.17490","title":"Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning","created":"2025-04-24","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":"2603.04333","title":"What Does Flow Matching Bring To TD Learning?","created":"2026-03-04","cited_by_count":2,"area":"diffusion"},{"id":"2603.13381","title":"Beyond Linearity in Attention Projections: The Case for Nonlinear Queries","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2505.01584","title":"Silent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adaptive Video Streaming","created":"2025-05-02","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":"2507.04683","title":"Recovering Plasticity of Neural Networks via Soft Weight Rescaling","created":"2025-07-07","cited_by_count":1,"area":null},{"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":"2508.18258","title":"ANO : Faster is Better in Noisy Landscape","created":"2025-08-25","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":"2512.23419","title":"The World Is Bigger! A Computationally-Embedded Perspective on the Big World Hypothesis","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2602.05619","title":"Mode-Dependent Rectification for Stable PPO Training","created":"2026-02-05","cited_by_count":1,"area":"deeprl"},{"id":"2604.01563","title":"Does Your Optimizer Care How You Normalize? Normalization-Optimizer Coupling in LLM Training","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2605.10734","title":"XQCfD: Accelerating Fast Actor-Critic Algorithms with Prior Data and Prior Policies","created":"2026-05-11","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":"2605.14587","title":"Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning","created":"2026-05-14","cited_by_count":1,"area":"deeprl"},{"id":"2606.09762","title":"Preserving Plasticity in Continual Learning via Dynamical Isometry","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.24752","title":"Can Scale Save Us From Plasticity Loss in Large Language Models?","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2410.12598","title":"Dynamic Learning Rate for Deep Reinforcement Learning: A Bandit Approach","created":"2024-10-16","cited_by_count":0,"area":"deeprl"},{"id":"2509.23750","title":"An Investigation of Batch Normalization in Off-Policy Actor-Critic Algorithms","created":"2025-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2511.07308","title":"Can Stationary Distributions of Scale-Invariant Neural Networks Be Described by the Thermodynamics of an Ideal Gas?","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2603.07787","title":"Vision Transformers that Never Stop Learning","created":"2026-03-08","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":"2603.21173","title":"Rethinking Plasticity in Deep Reinforcement Learning","created":"2026-03-22","cited_by_count":0,"area":"deeprl"},{"id":"2604.16426","title":"Functional Similarity Metric for Neural Networks: Overcoming Parametric Ambiguity via Activation Region Analysis","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2605.01131","title":"Forager: a lightweight testbed for continual learning with partial observability in RL","created":"2026-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2605.01567","title":"Feedback-Normalized Developer Memory for Reinforcement-Learning Coding Agents: A Safety-Gated MCP Architecture","created":"2026-05-02","cited_by_count":0,"area":"agents"},{"id":"2605.04368","title":"Extending Differential Temporal Difference Methods for Episodic Problems","created":"2026-05-06","cited_by_count":0,"area":"deeprl"},{"id":"2606.02194","title":"Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards","created":"2026-06-01","cited_by_count":0,"area":"offlinerl"},{"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":"2606.10448","title":"Mitigating Bias in Low-SNR Financial Reinforcement Learning via Quantum Representations","created":"2026-06-09","cited_by_count":0,"area":"deeprl"},{"id":"2606.14022","title":"Placing Degree Scales After LayerNorm","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.17922","title":"PRIME: Plasticity Recovery in Multi-Agent Environments for UAV-Assisted Emergency Communication Networks","created":"2026-07-20","cited_by_count":0,"area":null},{"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":"2608.18319","title":"SingularClip: Preventing Spectral Collapse to Maintain Plasticity in Continual and Reinforcement Learning","created":"2026-08-18","cited_by_count":0,"area":"deeprl"},{"id":"2609.06421","title":"On BatchNorm Forward Modes in Value-Based Reinforcement Learning","created":"2026-09-06","cited_by_count":0,"area":"deeprl"},{"id":"2609.20300","title":"Improving Generalization and Robustness in Offline Reinforcement Learning via Boundary-Aware Data Augmentation","created":"2026-08-22","cited_by_count":0,"area":"offlinerl"},{"id":"2610.02545","title":"Reward Inflation: A Healthy Stimulus for Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.03604","title":"Mastering Atari 2600 Games with Discovered Options","created":"2026-10-02","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}