{"total":116,"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":"2402.18762","title":"Disentangling the Causes of Plasticity Loss in Neural Networks","created":"2024-02-29","cited_by_count":86,"area":"deeprl"},{"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":"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":"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":"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":"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":"2506.00592","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","created":"2025-05-31","cited_by_count":22,"area":"deeprl"},{"id":"2412.07224","title":"Parseval Regularization for Continual Reinforcement Learning","created":"2024-12-10","cited_by_count":21,"area":"deeprl"},{"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":"2509.25174","title":"XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning","created":"2025-09-29","cited_by_count":17,"area":"deeprl"},{"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":"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":"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":"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":"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":"2501.16918","title":"On Rollouts in Model-Based Reinforcement Learning","created":"2025-01-28","cited_by_count":10,"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":"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":"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":"2507.11019","title":"Relative Entropy Pathwise Policy Optimization","created":"2025-07-15","cited_by_count":7,"area":"deeprl"},{"id":"2402.10228","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","created":"2024-02-05","cited_by_count":6,"area":"deeprl"},{"id":"2405.04342","title":"The Curse of Diversity in Ensemble-Based Exploration","created":"2024-05-07","cited_by_count":6,"area":"deeprl"},{"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":"2508.14881","title":"Compute-Optimal Scaling for Value-Based Deep RL","created":"2025-08-20","cited_by_count":6,"area":"deeprl"},{"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":"2407.06756","title":"Frequency and Generalisation of Periodic Activation Functions in Reinforcement Learning","created":"2024-07-09","cited_by_count":4,"area":"deeprl"},{"id":"2412.14312","title":"Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning","created":"2024-12-18","cited_by_count":4,"area":"deeprl"},{"id":"2502.20341","title":"Safety Representations for Safer Policy Learning","created":"2025-02-27","cited_by_count":4,"area":"deeprl"},{"id":"2504.09021","title":"A Champion-level Vision-based Reinforcement Learning Agent for Competitive Racing in Gran Turismo 7","created":"2025-04-12","cited_by_count":4,"area":"deeprl"},{"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":"2602.08690","title":"SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity","created":"2026-02-09","cited_by_count":4,"area":"deeprl"},{"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":"2410.11833","title":"Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions","created":"2024-10-15","cited_by_count":3,"area":"deeprl"},{"id":"2501.17842","title":"From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning","created":"2025-01-29","cited_by_count":3,"area":"deeprl"},{"id":"2511.21011","title":"Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning","created":"2025-11-26","cited_by_count":3,"area":"deeprl"},{"id":"2407.04864","title":"Augmented Bayesian Policy Search","created":"2024-07-05","cited_by_count":2,"area":"deeprl"},{"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":"2507.14736","title":"Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning","created":"2025-07-19","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":"2602.11800","title":"Temporal Difference Learning with Constrained Initial Representations","created":"2026-02-12","cited_by_count":2,"area":"deeprl"},{"id":"2604.01913","title":"The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning","created":"2026-04-02","cited_by_count":2,"area":"deeprl"},{"id":"2404.00651","title":"Learning Off-policy with Model-based Intrinsic Motivation For Active Online Exploration","created":"2024-03-31","cited_by_count":1,"area":"deeprl"},{"id":"2405.14629","title":"Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of Experiences","created":"2024-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2406.09079","title":"Hadamard Representation: Scaffolding Performance Across Model-free RL","created":"2024-06-13","cited_by_count":1,"area":"deeprl"},{"id":"2410.13490","title":"Novelty-based Sample Reuse for Continuous Robotics Control","created":"2024-10-17","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":"2508.01329","title":"Is Exploration or Optimization the Problem for Deep Reinforcement Learning?","created":"2025-08-02","cited_by_count":1,"area":"deeprl"},{"id":"2509.17092","title":"On the Limits of Tabular Hardness Metrics for Deep RL: A Study with the Pharos Benchmark","created":"2025-09-21","cited_by_count":1,"area":"deeprl"},{"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":"2601.21363","title":"Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control","created":"2026-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2603.09090","title":"Overcoming Valid Action Suppression in Unmasked Policy Gradient Algorithms","created":"2026-03-10","cited_by_count":1,"area":"deeprl"},{"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":"2604.25508","title":"Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty","created":"2026-04-28","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":"2605.21214","title":"Behavior-Consistent Deep Reinforcement Learning","created":"2026-05-20","cited_by_count":1,"area":"deeprl"},{"id":"2403.01014","title":"A Case for Validation Buffer in Pessimistic Actor-Critic","created":"2024-03-01","cited_by_count":0,"area":"deeprl"},{"id":"2407.11044","title":"Generalizing soft actor-critic algorithms to discrete action spaces","created":"2024-07-08","cited_by_count":0,"area":"deeprl"},{"id":"2503.00282","title":"Maintaining Plasticity in Reinforcement Learning: A Cost-Aware Framework for Aerial Robot Control in Non-stationary Environments","created":"2025-03-01","cited_by_count":0,"area":"deeprl"},{"id":"2504.08000","title":"Neuron-level Balance between Stability and Plasticity in Deep Reinforcement Learning","created":"2025-04-09","cited_by_count":0,"area":"deeprl"},{"id":"2506.13741","title":"PB$^2$: Preference Space Exploration via Population-Based Methods in Preference-Based Reinforcement Learning","created":"2025-06-16","cited_by_count":0,"area":"deeprl"},{"id":"2506.22566","title":"Exploration Behavior of Untrained Policies","created":"2025-06-27","cited_by_count":0,"area":"deeprl"},{"id":"2510.24432","title":"Fill in the Blanks: Accelerating Q-Learning with a Handful of Demonstrations in Sparse Reward Settings","created":"2025-10-28","cited_by_count":0,"area":"deeprl"},{"id":"2511.06895","title":"On The Presence of Double-Descent in Deep Reinforcement Learning","created":"2025-11-10","cited_by_count":0,"area":"deeprl"},{"id":"2512.17034","title":"GB-DQN: Gradient Boosted DQN Models for Non-stationary Reinforcement Learning","created":"2025-12-18","cited_by_count":0,"area":"deeprl"},{"id":"2601.19452","title":"APC-RL: Exceeding Data-Driven Behavior Priors with Adaptive Policy Composition","created":"2026-01-27","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":"2604.18978","title":"Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning","created":"2026-04-21","cited_by_count":0,"area":"deeprl"},{"id":"2605.07057","title":"From Causal Graphs to Markovian States: Multi-Order State Exposure for Deep RL","created":"2026-05-08","cited_by_count":0,"area":"deeprl"},{"id":"2605.10546","title":"Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning","created":"2026-05-11","cited_by_count":0,"area":"deeprl"},{"id":"2605.14350","title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","created":"2026-05-14","cited_by_count":0,"area":"deeprl"},{"id":"2605.22454","title":"Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning","created":"2026-05-21","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}