{"total":134,"rows":[{"id":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392,"area":null},{"id":"2410.12557","title":"One Step Diffusion via Shortcut Models","created":"2024-10-16","cited_by_count":391,"area":"diffusion"},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2201.13259","title":"Trajectory balance: Improved credit assignment in GFlowNets","created":"2022-01-31","cited_by_count":251,"area":null},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247,"area":null},{"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":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125,"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":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"area":"offlinerl"},{"id":"2406.09329","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","created":"2024-06-13","cited_by_count":89,"area":"offlinerl"},{"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":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"area":null},{"id":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2109.10813","title":"A Workflow for Offline Model-Free Robotic Reinforcement Learning","created":"2021-09-22","cited_by_count":69,"area":"offlinerl"},{"id":"2112.04716","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","created":"2021-12-09","cited_by_count":66,"area":"offlinerl"},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65,"area":null},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"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":"2206.10369","title":"The State of Sparse Training in Deep Reinforcement Learning","created":"2022-06-17","cited_by_count":61,"area":null},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"area":null},{"id":"2110.14020","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","created":"2021-10-26","cited_by_count":50,"area":"offlinerl"},{"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":"2306.13812","title":"Maintaining Plasticity in Deep Continual Learning","created":"2023-06-23","cited_by_count":43,"area":null},{"id":"2402.02651","title":"Vision-Language Models Provide Promptable Representations for Reinforcement Learning","created":"2024-02-05","cited_by_count":41,"area":"mllm"},{"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":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"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":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32,"area":null},{"id":"2205.11027","title":"When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning","created":"2022-05-23","cited_by_count":31,"area":"offlinerl"},{"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":"2203.00543","title":"On the Generalization of Representations in Reinforcement Learning","created":"2022-03-01","cited_by_count":28,"area":null},{"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":"2207.02099","title":"An Empirical Study of Implicit Regularization in Deep Offline RL","created":"2022-07-05","cited_by_count":24,"area":"offlinerl"},{"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":"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":"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":"2206.04672","title":"Overcoming the Spectral Bias of Neural Value Approximation","created":"2022-06-09","cited_by_count":19,"area":null},{"id":"2202.08539","title":"When, where, and how to add new neurons to ANNs","created":"2022-02-17","cited_by_count":18,"area":null},{"id":"2410.07994","title":"Neuroplastic Expansion in Deep Reinforcement Learning","created":"2024-10-10","cited_by_count":18,"area":"deeprl"},{"id":"2112.03257","title":"Functional Regularization for Reinforcement Learning via Learned Fourier Features","created":"2021-12-06","cited_by_count":17,"area":null},{"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":"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":"2509.23808","title":"Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning","created":"2025-09-28","cited_by_count":17,"area":"lr"},{"id":"2205.15460","title":"Critic Sequential Monte Carlo","created":"2022-05-30","cited_by_count":16,"area":null},{"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":"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":"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":"2211.01052","title":"Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints","created":"2022-11-02","cited_by_count":13,"area":"offlinerl"},{"id":"2211.00863","title":"Behavior Prior Representation learning for Offline Reinforcement Learning","created":"2022-11-02","cited_by_count":12,"area":"offlinerl"},{"id":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2401.05444","title":"Fully Spiking Actor Network with Intra-layer Connections for Reinforcement Learning","created":"2024-01-09","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":"2506.17204","title":"Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":11,"area":"deeprl"},{"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":"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":"2603.12480","title":"One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies","created":"2026-03-12","cited_by_count":7,"area":"diffusion"},{"id":"2106.14993","title":"Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment","created":"2021-06-28","cited_by_count":6,"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":"2508.00212","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2508.14881","title":"Compute-Optimal Scaling for Value-Based Deep RL","created":"2025-08-20","cited_by_count":6,"area":"deeprl"},{"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":"2302.00141","title":"Revisiting Bellman Errors for Offline Model Selection","created":"2023-01-31","cited_by_count":5,"area":"offlinerl"},{"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":"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":"2406.06309","title":"Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?","created":"2024-06-10","cited_by_count":4,"area":"offlinerl"},{"id":"2407.06756","title":"Frequency and Generalisation of Periodic Activation Functions in Reinforcement Learning","created":"2024-07-09","cited_by_count":4,"area":"deeprl"},{"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":"2506.04398","title":"Bridging the Performance Gap Between Target-Free and Target-Based Reinforcement Learning","created":"2025-06-04","cited_by_count":4,"area":"deeprl"},{"id":"2410.15858","title":"Towards Optimal Adapter Placement for Efficient Transfer Learning","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2409.07606","title":"The Role of Deep Learning Regularizations on Actors in Offline RL","created":"2024-09-11","cited_by_count":2,"area":"offlinerl"},{"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":"2508.06871","title":"Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning","created":"2025-08-09","cited_by_count":2,"area":"deeprl"},{"id":"2512.01034","title":"AltNet: Addressing the Plasticity-Stability Dilemma in Reinforcement Learning","created":"2025-11-30","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":"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":"2303.01391","title":"The Ladder in Chaos: A Simple and Effective Improvement to General DRL Algorithms by Policy Path Trimming and Boosting","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2312.05787","title":"Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization","created":"2023-12-10","cited_by_count":1,"area":null}],"next_cursor":"100"}