{"total":90,"rows":[{"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":"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":"2504.11054","title":"Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models","created":"2025-04-15","cited_by_count":56,"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":"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":"2505.22642","title":"FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control","created":"2025-05-28","cited_by_count":44,"area":"deeprl"},{"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":"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":"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":"2506.15544","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":"2502.07523","title":"Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization","created":"2025-02-11","cited_by_count":19,"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":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","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":"2512.01996","title":"Learning Sim-to-Real Humanoid Locomotion in 15 Minutes","created":"2025-12-01","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":"2410.01930","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":"2410.22391","title":"A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks","created":"2024-10-29","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":"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":"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":"2402.03903","title":"Averaging $n$-step Returns Reduces Variance in Reinforcement Learning","created":"2024-02-06","cited_by_count":9,"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":"2602.01439","title":"TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse","created":"2026-02-01","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":"2407.04522","title":"Graph Reinforcement Learning for Power Grids: A Comprehensive Survey","created":"2024-07-05","cited_by_count":7,"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":"2412.14355","title":"Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference","created":"2024-12-18","cited_by_count":7,"area":"deeprl"},{"id":"2501.08669","title":"SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning","created":"2025-01-15","cited_by_count":7,"area":"deeprl"},{"id":"2505.15345","title":"Hadamax Encoding: Elevating Performance in Model-Free Atari","created":"2025-05-21","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":"2510.21110","title":"Confounding Robust Deep Reinforcement Learning: A Causal Approach","created":"2025-10-24","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":"2503.01437","title":"Eau De $Q$-Network: Adaptive Distillation of Neural Networks in Deep Reinforcement Learning","created":"2025-03-03","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":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","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":"2406.06037","title":"Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning","created":"2024-06-10","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":"2506.04398","title":"Bridging the Performance Gap Between Target-Free and Target-Based Reinforcement Learning","created":"2025-06-04","cited_by_count":4,"area":"deeprl"},{"id":"2505.24784","title":"AXIOM: Learning to Play Games in Minutes with Expanding Object-Centric Models","created":"2025-05-30","cited_by_count":3,"area":"deeprl"},{"id":"2506.18482","title":"Reliability-Adjusted Prioritized Experience Replay","created":"2025-06-23","cited_by_count":3,"area":"deeprl"},{"id":"2510.16175","title":"The Formalism-Implementation Gap in Reinforcement Learning Research","created":"2025-10-17","cited_by_count":3,"area":"deeprl"},{"id":"2510.22833","title":"Toward Agents That Reason About Their Computation","created":"2025-10-26","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":"2402.06912","title":"Solving Deep Reinforcement Learning Tasks with Evolution Strategies and Linear Policy Networks","created":"2024-02-10","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":"2510.23216","title":"Human-Like Goalkeeping in a Realistic Football Simulation: a Sample-Efficient Reinforcement Learning Approach","created":"2025-10-27","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":"2605.31273","title":"Survival Reinforcement Learning: Toward Scalable Self-Supervised RL","created":"2026-05-29","cited_by_count":2,"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":"2506.11706","title":"Growing with Experience: Growing Neural Networks in Deep Reinforcement Learning","created":"2025-06-13","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":"2606.19357","title":"Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on Robots","created":"2026-05-29","cited_by_count":1,"area":"deeprl"},{"id":"2606.20411","title":"Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning","created":"2026-06-18","cited_by_count":1,"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":"2410.06317","title":"Learning in complex action spaces without policy gradients","created":"2024-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2412.17344","title":"Reinforcement Learning with a Focus on Adjusting Policies to Reach Targets","created":"2024-12-23","cited_by_count":0,"area":"deeprl"},{"id":"2507.11975","title":"Online Training and Pruning of Deep Reinforcement Learning Networks","created":"2025-07-16","cited_by_count":0,"area":"deeprl"},{"id":"2510.22859","title":"Guardian: Decoupling Exploration from Safety in Reinforcement Learning","created":"2025-10-26","cited_by_count":0,"area":"deeprl"},{"id":"2512.20513","title":"Recurrent Off-Policy Deep Reinforcement Learning Doesn't Have to be Slow","created":"2025-12-23","cited_by_count":0,"area":"deeprl"},{"id":"2603.29501","title":"Target-Aligned Reinforcement Learning","created":"2026-03-31","cited_by_count":0,"area":"deeprl"},{"id":"2604.20381","title":"Distributional Value Estimation Without Target Networks for Robust Quality-Diversity","created":"2026-04-22","cited_by_count":0,"area":"deeprl"},{"id":"2605.05812","title":"Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities","created":"2026-05-07","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":"2606.05555","title":"Representation Learning Enables Scalable Multitask Deep Reinforcement Learning","created":"2026-06-04","cited_by_count":0,"area":"deeprl"},{"id":"2606.14029","title":"Utility-Constrained Policy Optimization","created":"2026-06-12","cited_by_count":0,"area":"deeprl"},{"id":"2606.20210","title":"Augmenting Game AI with Deep Reinforcement Learning","created":"2026-06-18","cited_by_count":0,"area":"deeprl"},{"id":"2608.03069","title":"Revisiting TD Target Aggregation under Uncertainty in Q-Learning","created":"2026-08-04","cited_by_count":0,"area":"deeprl"},{"id":"2608.05989","title":"Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control","created":"2026-08-06","cited_by_count":0,"area":"deeprl"},{"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":"2608.16182","title":"Understanding and Stabilizing Deep Q-Learning via Controlled Bootstrapping and Regulated Value Dynamics","created":"2026-08-17","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":"2608.26571","title":"Arrive and Survive: Scaling Safe Goal-Conditioned Policy Learning from One-Bit Failure Signals","created":"2026-08-27","cited_by_count":0,"area":"deeprl"},{"id":"2610.02801","title":"VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning","created":"2026-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2610.03475","title":"Single or Multiple Policies for Phase-Structured Reinforcement Learning?","created":"2026-10-02","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}