{"total":86,"rows":[{"id":"2403.03950","title":"Stop Regressing: Training Value Functions via Classification for Scalable Deep RL","created":"2024-03-06","cited_by_count":144,"area":"deeprl"},{"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":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2407.01800","title":"Normalization and effective learning rates in reinforcement learning","created":"2024-07-01","cited_by_count":58,"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":"2406.06811","title":"Learning Continually by Spectral Regularization","created":"2024-06-10","cited_by_count":34,"area":null},{"id":"2407.01704","title":"Weight Clipping for Deep Continual and Reinforcement Learning","created":"2024-07-01","cited_by_count":29,"area":"deeprl"},{"id":"2405.00662","title":"No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO","created":"2024-05-01","cited_by_count":27,"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":"2506.00592","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","created":"2025-05-31","cited_by_count":22,"area":"deeprl"},{"id":"2410.07994","title":"Neuroplastic Expansion in Deep Reinforcement Learning","created":"2024-10-10","cited_by_count":18,"area":"deeprl"},{"id":"2411.15370","title":"Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers","created":"2024-11-22","cited_by_count":18,"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":"2405.16642","title":"Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning","created":"2024-05-26","cited_by_count":17,"area":"deeprl"},{"id":"2409.04792","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","created":"2024-09-07","cited_by_count":17,"area":"deeprl"},{"id":"2411.04034","title":"Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset","created":"2024-11-06","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":"2407.07082","title":"Can Learned Optimization Make Reinforcement Learning Less Difficult?","created":"2024-07-09","cited_by_count":14,"area":"deeprl"},{"id":"2410.01930","title":"Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL","created":"2024-10-02","cited_by_count":14,"area":"deeprl"},{"id":"2410.20634","title":"Plastic Learning with Deep Fourier Features","created":"2024-10-27","cited_by_count":14,"area":null},{"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":"2410.20098","title":"Self-Normalized Resets for Plasticity in Continual Learning","created":"2024-10-26","cited_by_count":11,"area":null},{"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":"2411.03820","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","created":"2024-11-06","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":"2502.01342","title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","created":"2025-02-03","cited_by_count":6,"area":null},{"id":"2509.22335","title":"Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2509.22562","title":"Activation Function Design Sustains Plasticity in Continual Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2506.10710","title":"Continual Hyperbolic Learning of Instances and Classes","created":"2025-06-12","cited_by_count":5,"area":null},{"id":"2503.17500","title":"Variance Control via Weight Rescaling in LLM Pre-training","created":"2025-03-21","cited_by_count":4,"area":null},{"id":"2506.01016","title":"Optimistic critics can empower small actors","created":"2025-06-01","cited_by_count":4,"area":"deeprl"},{"id":"2605.09044","title":"Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective","created":"2026-05-09","cited_by_count":4,"area":null},{"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":"2412.18790","title":"Torque-Aware Momentum","created":"2024-12-25","cited_by_count":2,"area":null},{"id":"2503.01468","title":"Overcoming Non-stationary Dynamics with Evidential Proximal Policy Optimization","created":"2025-03-03","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":"2505.09486","title":"Preserving Plasticity in Continual Learning with Adaptive Linearity Injection","created":"2025-05-14","cited_by_count":2,"area":null},{"id":"2508.00127","title":"Structured Transformations for Stable and Interpretable Neural Computation","created":"2025-07-31","cited_by_count":2,"area":null},{"id":"2508.06871","title":"Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning","created":"2025-08-09","cited_by_count":2,"area":"deeprl"},{"id":"2510.06548","title":"Reusing Overtrained Language Models Saturates Scaling","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2512.01034","title":"AltNet: Addressing the Plasticity-Stability Dilemma in Reinforcement Learning","created":"2025-11-30","cited_by_count":2,"area":"deeprl"},{"id":"2602.09234","title":"Do Neural Networks Lose Plasticity in a Gradually Changing World?","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2602.16740","title":"Quantifying LLM Attention-Head Stability: Implications for Circuit Universality","created":"2026-02-17","cited_by_count":2,"area":"mechinterp"},{"id":"2605.04712","title":"SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning","created":"2026-05-06","cited_by_count":2,"area":"moe"},{"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":"2507.04683","title":"Recovering Plasticity of Neural Networks via Soft Weight Rescaling","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2508.02126","title":"Understanding Learning Dynamics Through Structured Representations","created":"2025-08-04","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":"2509.19698","title":"A Unified Noise-Curvature View of Loss of Trainability","created":"2025-09-24","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":"2602.02799","title":"Joint Learning of Hierarchical Neural Options and Abstract World Model","created":"2026-02-02","cited_by_count":1,"area":"wm"},{"id":"2604.09028","title":"Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks","created":"2026-04-10","cited_by_count":1,"area":"moe"},{"id":"2604.15414","title":"Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning","created":"2026-04-16","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":"2605.21214","title":"Behavior-Consistent Deep Reinforcement Learning","created":"2026-05-20","cited_by_count":1,"area":"deeprl"},{"id":"2605.26357","title":"Balancing Plasticity and Stability with Fast and Slow Successor Features","created":"2026-05-25","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":"2507.10637","title":"A Simple Baseline for Stable and Plastic Neural Networks","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2602.04555","title":"Finding Structure in Continual Learning","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.21173","title":"Rethinking Plasticity in Deep Reinforcement Learning","created":"2026-03-22","cited_by_count":0,"area":"deeprl"},{"id":"2604.18857","title":"Task Switching Without Forgetting via Proximal Decoupling","created":"2026-04-20","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":"2605.06834","title":"Attribution-Based Neuron Utility for Plasticity Restoration in Deep Networks","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.23565","title":"Understanding Goal Generalisation in Sequential Reinforcement Learning","created":"2026-05-22","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":"2606.25527","title":"Beyond One-Size-Fits-All: Diagnosis-Driven Online Reinforcement Learning with Offline Priors","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.00634","title":"Loss Smoothing for Stable Adaptation Under Distribution Shift","created":"2026-07-01","cited_by_count":0,"area":"deeprl"},{"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":"2607.24996","title":"Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning","created":"2026-07-27","cited_by_count":0,"area":"deeprl"},{"id":"2607.27281","title":"The Kinetics of Training: A Driven-Nucleation Rate Law for Emergence, Plasticity Loss, and Circuit Control in Language Models","created":"2026-07-29","cited_by_count":0,"area":"mechinterp"},{"id":"2608.04358","title":"NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning","created":"2026-08-05","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":"2609.01768","title":"Emergence of Fibrations, Compression, and Symmetry Breaking in Artificial Neural Networks","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.31589","title":"Common-Mode Collapse and Recovery in Direct Feedback Alignment","created":"2026-09-25","cited_by_count":0,"area":null},{"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":"2609.33106","title":"CARVE: Breaking Data Barriers in Chip Placement by Harnessing Reusable Expertise","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33127","title":"Policy Plasticity Matters in Offline-to-Online Reinforcement Learning: Refitting Offline Policies for Online Adaptation","created":"2026-09-27","cited_by_count":0,"area":"offlinerl"},{"id":"2610.01583","title":"Continual Reinforcement Learning with Neuroevolution","created":"2026-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.02545","title":"Reward Inflation: A Healthy Stimulus for Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.09621","title":"When does a network's training history predict its future learning better than its current state? Evidence from a response probe and a forecasting screen","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}