{"total":174,"rows":[{"id":"2410.12557","title":"One Step Diffusion via Shortcut Models","created":"2024-10-16","cited_by_count":391,"area":"diffusion"},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147,"area":null},{"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":"2402.18762","title":"Disentangling the Causes of Plasticity Loss in Neural Networks","created":"2024-02-29","cited_by_count":86,"area":"deeprl"},{"id":"2402.08609","title":"Mixtures of Experts Unlock Parameter Scaling for Deep RL","created":"2024-02-13","cited_by_count":78,"area":"moe"},{"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":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74,"area":null},{"id":"2308.11958","title":"Maintaining Plasticity in Continual Learning via Regenerative Regularization","created":"2023-08-23","cited_by_count":65,"area":null},{"id":"2407.01800","title":"Normalization and effective learning rates in reinforcement learning","created":"2024-07-01","cited_by_count":58,"area":"deeprl"},{"id":"2403.00514","title":"Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning","created":"2024-03-01","cited_by_count":50,"area":"deeprl"},{"id":"2310.19668","title":"DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization","created":"2023-10-30","cited_by_count":47,"area":null},{"id":"2410.23208","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","created":"2024-10-30","cited_by_count":45,"area":null},{"id":"2306.13812","title":"Maintaining Plasticity in Deep Continual Learning","created":"2023-06-23","cited_by_count":43,"area":null},{"id":"2306.10711","title":"PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning","created":"2023-06-19","cited_by_count":42,"area":null},{"id":"2407.09705","title":"Diagnosing and Re-learning for Balanced Multimodal Learning","created":"2024-07-12","cited_by_count":41,"area":null},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"id":"2402.12479","title":"In value-based deep reinforcement learning, a pruned network is a good network","created":"2024-02-19","cited_by_count":39,"area":"deeprl"},{"id":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38,"area":"deeprl"},{"id":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36,"area":null},{"id":"2406.06811","title":"Learning Continually by Spectral Regularization","created":"2024-06-10","cited_by_count":34,"area":null},{"id":"2402.08552","title":"Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases","created":"2024-02-13","cited_by_count":30,"area":"diffusion"},{"id":"2407.01704","title":"Weight Clipping for Deep Continual and Reinforcement Learning","created":"2024-07-01","cited_by_count":29,"area":"deeprl"},{"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":"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":"2312.00246","title":"Directions of Curvature as an Explanation for Loss of Plasticity","created":"2023-11-30","cited_by_count":26,"area":null},{"id":"2405.19153","title":"A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning","created":"2024-05-29","cited_by_count":26,"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":"2410.14972","title":"MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning","created":"2024-10-19","cited_by_count":23,"area":"moe"},{"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":"2506.00592","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","created":"2025-05-31","cited_by_count":22,"area":"deeprl"},{"id":"2406.17523","title":"On the consistency of hyper-parameter selection in value-based deep reinforcement learning","created":"2024-06-25","cited_by_count":21,"area":"deeprl"},{"id":"2406.18420","title":"Mixture of Experts in a Mixture of RL settings","created":"2024-06-26","cited_by_count":21,"area":"moe"},{"id":"2412.07224","title":"Parseval Regularization for Continual Reinforcement Learning","created":"2024-12-10","cited_by_count":21,"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":"2502.11477","title":"Learning to Sample Effective and Diverse Prompts for Text-to-Image Generation","created":"2025-02-17","cited_by_count":17,"area":"diffusion"},{"id":"2507.12224","title":"Optimizers Qualitatively Alter Solutions And We Should Leverage This","created":"2025-07-16","cited_by_count":17,"area":null},{"id":"2402.14528","title":"ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization","created":"2024-02-22","cited_by_count":16,"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":"2502.04327","title":"Value-Based Deep RL Scales Predictably","created":"2025-02-06","cited_by_count":15,"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":"2410.00564","title":"Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining","created":"2024-10-01","cited_by_count":14,"area":"wm"},{"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":"2304.14082","title":"JaxPruner: A concise library for sparsity research","created":"2023-04-27","cited_by_count":13,"area":null},{"id":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13,"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":"2402.02720","title":"Discounted Adaptive Online Learning: Towards Better Regularization","created":"2024-02-05","cited_by_count":12,"area":null},{"id":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2410.00051","title":"Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization","created":"2024-09-28","cited_by_count":11,"area":"diffusion"},{"id":"2410.20098","title":"Self-Normalized Resets for Plasticity in Continual Learning","created":"2024-10-26","cited_by_count":11,"area":null},{"id":"2412.17113","title":"Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps","created":"2024-12-22","cited_by_count":11,"area":"deeprl"},{"id":"2506.14990","title":"MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning","created":"2025-06-17","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":"2507.02712","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":"2503.05126","title":"Multi-Task Reinforcement Learning Enables Parameter Scaling","created":"2025-03-07","cited_by_count":8,"area":"deeprl"},{"id":"2404.12754","title":"Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation","created":"2024-04-19","cited_by_count":7,"area":"deeprl"},{"id":"2410.23495","title":"DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity","created":"2024-10-30","cited_by_count":7,"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":"2412.11979","title":"AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws","created":"2024-12-16","cited_by_count":7,"area":null},{"id":"2505.15345","title":"Hadamax Encoding: Elevating Performance in Model-Free Atari","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2507.08761","title":"Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data","created":"2025-07-11","cited_by_count":7,"area":"deeprl"},{"id":"2512.11668","title":"Bridging Streaming Continual Learning via In-Context Large Tabular Models","created":"2025-12-12","cited_by_count":7,"area":null},{"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":"2403.07688","title":"Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2405.04342","title":"The Curse of Diversity in Ensemble-Based Exploration","created":"2024-05-07","cited_by_count":6,"area":"deeprl"},{"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":"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":"2508.00212","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","created":"2025-07-31","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":"2410.23810","title":"CALE: Continuous Arcade Learning Environment","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2510.00304","title":"Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity","created":"2025-09-30","cited_by_count":5,"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":"2403.05066","title":"Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning","created":"2024-03-08","cited_by_count":4,"area":"deeprl"},{"id":"2503.20018","title":"Experience Replay Addresses Loss of Plasticity in Continual Learning","created":"2025-03-25","cited_by_count":4,"area":null},{"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":"2506.01016","title":"Optimistic critics can empower small actors","created":"2025-06-01","cited_by_count":4,"area":"deeprl"},{"id":"2508.06412","title":"Sample-efficient LLM Optimization with Reset Replay","created":"2025-08-08","cited_by_count":4,"area":"lr"},{"id":"2510.01460","title":"The Three Regimes of Offline-to-Online Reinforcement Learning","created":"2025-10-01","cited_by_count":4,"area":"offlinerl"},{"id":"2602.01460","title":"Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator","created":"2026-02-01","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":"2606.27715","title":"Aurora: A Leverage-Aware Spectral Optimizer","created":"2026-06-26","cited_by_count":4,"area":null},{"id":"2405.16195","title":"Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning","created":"2024-05-25","cited_by_count":3,"area":"deeprl"},{"id":"2503.05246","title":"Mastering Continual Reinforcement Learning through Fine-Grained Sparse Network Allocation and Dormant Neuron Exploration","created":"2025-03-07","cited_by_count":3,"area":"deeprl"},{"id":"2509.07945","title":"One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning","created":"2025-09-09","cited_by_count":3,"area":"wm"},{"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":"2407.03436","title":"A Role of Environmental Complexity on Representation Learning in Deep Reinforcement Learning Agents","created":"2024-07-03","cited_by_count":2,"area":"deeprl"},{"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":"2504.14677","title":"Evaluating Temporal Plasticity in Foundation Time Series Models for Incremental Fine-tuning","created":"2025-04-20","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"}],"next_cursor":"100"}