{"total":247,"rows":[{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478,"area":"wm"},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228,"area":"agents"},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174,"area":null},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174,"area":null},{"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":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2303.07507","title":"Loss of Plasticity in Continual Deep Reinforcement Learning","created":"2023-03-13","cited_by_count":121,"area":null},{"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":"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":"2307.09218","title":"A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning","created":"2023-07-16","cited_by_count":69,"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":"2412.07762","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","created":"2024-12-10","cited_by_count":63,"area":"offlinerl"},{"id":"2206.10369","title":"The State of Sparse Training in Deep Reinforcement Learning","created":"2022-06-17","cited_by_count":61,"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":"2502.02316","title":"DIME:Diffusion-Based Maximum Entropy Reinforcement Learning","created":"2025-02-04","cited_by_count":58,"area":"diffusion"},{"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":"2405.06639","title":"Value Augmented Sampling for Language Model Alignment and Personalization","created":"2024-05-10","cited_by_count":49,"area":"alignment"},{"id":"2310.19668","title":"DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization","created":"2023-10-30","cited_by_count":47,"area":null},{"id":"2306.13812","title":"Maintaining Plasticity in Deep Continual Learning","created":"2023-06-23","cited_by_count":43,"area":null},{"id":"2307.01163","title":"Improving Language Plasticity via Pretraining with Active Forgetting","created":"2023-07-03","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":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"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":"2304.10466","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","created":"2023-04-20","cited_by_count":36,"area":null},{"id":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36,"area":null},{"id":"2312.07551","title":"Language Model Alignment with Elastic Reset","created":"2023-12-06","cited_by_count":34,"area":"alignment"},{"id":"2406.06811","title":"Learning Continually by Spectral Regularization","created":"2024-06-10","cited_by_count":34,"area":null},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"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":"2306.17833","title":"Resetting the Optimizer in Deep RL: An Empirical Study","created":"2023-06-30","cited_by_count":26,"area":null},{"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":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2401.11963","title":"Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms","created":"2024-01-22","cited_by_count":26,"area":"deeprl"},{"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":"2310.17634","title":"Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion","created":"2023-10-26","cited_by_count":24,"area":null},{"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":"2506.00592","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","created":"2025-05-31","cited_by_count":22,"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":"2411.00062","title":"Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play","created":"2024-10-31","cited_by_count":21,"area":"alignment"},{"id":"2412.07224","title":"Parseval Regularization for Continual Reinforcement Learning","created":"2024-12-10","cited_by_count":21,"area":"deeprl"},{"id":"2312.11669","title":"Prediction and Control in Continual Reinforcement Learning","created":"2023-12-18","cited_by_count":19,"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":"2402.05828","title":"Discovering Temporally-Aware Reinforcement Learning Algorithms","created":"2024-02-08","cited_by_count":18,"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":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","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":"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":"2509.25174","title":"XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning","created":"2025-09-29","cited_by_count":17,"area":"deeprl"},{"id":"2211.11030","title":"Adversarial Cheap Talk","created":"2022-11-20","cited_by_count":16,"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":"2410.09163","title":"Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models","created":"2024-10-11","cited_by_count":16,"area":"deeprl"},{"id":"2212.07536","title":"Robust Policy Optimization in Deep Reinforcement Learning","created":"2022-12-14","cited_by_count":15,"area":null},{"id":"2310.18777","title":"Improving Compositional Generalization Using Iterated Learning and Simplicial Embeddings","created":"2023-10-28","cited_by_count":15,"area":null},{"id":"2502.04327","title":"Value-Based Deep RL Scales Predictably","created":"2025-02-06","cited_by_count":15,"area":"deeprl"},{"id":"2406.17718","title":"When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning","created":"2024-06-25","cited_by_count":14,"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":"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":"2301.07799","title":"A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems","created":"2023-01-18","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":"2305.18443","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","created":"2023-05-29","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":"2404.02113","title":"Position: Lifetime tuning is incompatible with continual reinforcement learning","created":"2024-04-02","cited_by_count":11,"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":"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":"2506.17204","title":"Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":11,"area":"deeprl"},{"id":"2306.02419","title":"Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL","created":"2023-06-04","cited_by_count":10,"area":null},{"id":"2311.15951","title":"Replay across Experiments: A Natural Extension of Off-Policy RL","created":"2023-11-27","cited_by_count":10,"area":null},{"id":"2501.16918","title":"On Rollouts in Model-Based Reinforcement Learning","created":"2025-01-28","cited_by_count":10,"area":"deeprl"},{"id":"2505.19552","title":"On scalable and efficient training of diffusion samplers","created":"2025-05-26","cited_by_count":10,"area":"diffusion"},{"id":"2605.02105","title":"Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting","created":"2026-05-04","cited_by_count":10,"area":null},{"id":"2310.15017","title":"Mind the Model, Not the Agent: The Primacy Bias in Model-based RL","created":"2023-10-23","cited_by_count":9,"area":"wm"},{"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":"2305.16379","title":"Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning","created":"2023-05-25","cited_by_count":8,"area":null},{"id":"2306.05637","title":"On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2406.00392","title":"Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning","created":"2024-06-01","cited_by_count":8,"area":"deeprl"},{"id":"2503.08375","title":"Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion","created":"2025-03-11","cited_by_count":8,"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":"2602.18037","title":"Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards","created":"2026-02-20","cited_by_count":8,"area":"alignment"},{"id":"2306.01276","title":"Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2310.08558","title":"Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias","created":"2023-10-12","cited_by_count":7,"area":"offlinerl"},{"id":"2310.17786","title":"Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates","created":"2023-10-26","cited_by_count":7,"area":null},{"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":"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}],"next_cursor":"100"}