{"total":78,"rows":[{"id":"2506.21734","title":"Hierarchical Reasoning Model","created":"2025-06-26","cited_by_count":177,"area":"lr"},{"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":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"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":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38,"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":"2412.12089","title":"Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation","created":"2024-12-16","cited_by_count":20,"area":"deeprl"},{"id":"2407.19396","title":"NAVIX: Scaling MiniGrid Environments with JAX","created":"2024-07-28","cited_by_count":18,"area":"deeprl"},{"id":"2503.03660","title":"Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns","created":"2025-03-05","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":"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":"2507.23172","title":"Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks","created":"2025-07-31","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":"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":"2509.08660","title":"Replicable Reinforcement Learning with Linear Function Approximation","created":"2025-09-10","cited_by_count":7,"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":"2510.01764","title":"Octax: Accelerated CHIP-8 Arcade Environments for Reinforcement Learning in JAX","created":"2025-10-02","cited_by_count":5,"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":"2603.09036","title":"SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding","created":"2026-03-10","cited_by_count":5,"area":null},{"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":"2606.00151","title":"Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying","created":"2026-05-29","cited_by_count":5,"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":"2506.06981","title":"Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments","created":"2025-06-08","cited_by_count":4,"area":"deeprl"},{"id":"2511.07328","title":"Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training","created":"2025-11-10","cited_by_count":4,"area":"rag"},{"id":"2501.06058","title":"Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot Coordination","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2503.01450","title":"Investigating Memory in Model-Free RL with POPGym Arcade","created":"2025-03-03","cited_by_count":3,"area":"deeprl"},{"id":"2510.12312","title":"Deep SPI: Safe Policy Improvement via World Models","created":"2025-10-14","cited_by_count":3,"area":"wm"},{"id":"2510.17697","title":"A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning","created":"2025-10-20","cited_by_count":3,"area":null},{"id":"2512.14202","title":"Understanding and Improving Hyperbolic Deep Reinforcement Learning","created":"2025-12-16","cited_by_count":3,"area":"deeprl"},{"id":"2503.11019","title":"Residual Policy Gradient: A Reward View of KL-regularized Objective","created":"2025-03-14","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":"2506.20061","title":"Learning Instruction-Following Policies through Open-Ended Instruction Relabeling with Large Language Models","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2510.02590","title":"Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning","created":"2025-10-02","cited_by_count":2,"area":"deeprl"},{"id":"2511.04904","title":"Multi-Agent Craftax: Benchmarking Open-Ended Multi-Agent Reinforcement Learning at the Hyperscale","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2602.11800","title":"Temporal Difference Learning with Constrained Initial Representations","created":"2026-02-12","cited_by_count":2,"area":"deeprl"},{"id":"2602.21203","title":"Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics","created":"2026-02-24","cited_by_count":2,"area":"deeprl"},{"id":"2606.08340","title":"Benchmarking Open-Ended Multi-Agent Coordination in Language Agents","created":"2026-06-06","cited_by_count":2,"area":"agents"},{"id":"2505.06771","title":"JaxRobotarium: Training and Deploying Multi-Robot Policies in 10 Minutes","created":"2025-05-10","cited_by_count":1,"area":"deeprl"},{"id":"2505.21119","title":"Universal Value-Function Uncertainties","created":"2025-05-27","cited_by_count":1,"area":"offlinerl"},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.07452","title":"Stackelberg Coupling of Online Representation Learning and Reinforcement Learning","created":"2025-08-10","cited_by_count":1,"area":"deeprl"},{"id":"2508.07746","title":"A Tutorial: An Intuitive Explanation of Offline Reinforcement Learning Theory","created":"2025-08-11","cited_by_count":1,"area":"offlinerl"},{"id":"2510.01105","title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2602.03301","title":"Periodic Regularized Q-Learning","created":"2026-02-03","cited_by_count":1,"area":"deeprl"},{"id":"2603.12612","title":"FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control","created":"2026-03-13","cited_by_count":1,"area":"deeprl"},{"id":"2604.01613","title":"Pseudo-Quantized Actor-Critic Algorithm for Robustness to Noisy Temporal Difference Error","created":"2026-04-02","cited_by_count":1,"area":"deeprl"},{"id":"2606.21173","title":"Inverting the Bellman Equation: From $Q$-Values to World Models","created":"2026-06-19","cited_by_count":1,"area":"wm"},{"id":"2606.28433","title":"Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxy","created":"2026-06-26","cited_by_count":1,"area":"deeprl"},{"id":"2410.01643","title":"Stable Offline Value Function Learning with Bisimulation-based Representations","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2502.17498","title":"Improving Value-based Process Verifier via Structural Prior Injection","created":"2025-02-21","cited_by_count":0,"area":"lr"},{"id":"2505.08222","title":"Scaling Multi Agent Reinforcement Learning for Underwater Acoustic Tracking via Autonomous Vehicles","created":"2025-05-13","cited_by_count":0,"area":"driving"},{"id":"2508.21488","title":"Priors Matter: Addressing Misspecification in Bayesian Deep Q-Learning","created":"2025-08-29","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":"2602.01665","title":"TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.19864","title":"NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.27162","title":"A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.05481","title":"Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL","created":"2026-05-06","cited_by_count":0,"area":"deeprl"},{"id":"2605.21557","title":"Scalable Reinforcement Learning via Adaptive Batch Scaling","created":"2026-05-20","cited_by_count":0,"area":"deeprl"},{"id":"2605.23551","title":"Goal-Conditioned Agents that Learn Everything All at Once","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2605.24975","title":"Bridging the Gap: Enabling Soft Actor Critic for High Performance Legged Locomotion","created":"2026-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2605.26012","title":"Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement Learning","created":"2026-05-25","cited_by_count":0,"area":"deeprl"},{"id":"2605.31222","title":"Multivariate Distributional Reinforcement Learning Using Sliced Divergences","created":"2026-05-29","cited_by_count":0,"area":"deeprl"},{"id":"2606.00880","title":"Task diversity produces systematic transfer but inhibits continual reinforcement learning","created":"2026-05-30","cited_by_count":0,"area":"deeprl"},{"id":"2606.14130","title":"Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.19397","title":"Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.28916","title":"Gated Q-learning: Add Off-Policy Bias to Taste","created":"2026-07-31","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":"2608.07335","title":"A Progressive Design Study of Visual Encoders and Value Estimation for Replay-Free Parallelized Q-Learning","created":"2026-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2609.06421","title":"On BatchNorm Forward Modes in Value-Based Reinforcement Learning","created":"2026-09-06","cited_by_count":0,"area":"deeprl"},{"id":"2609.07575","title":"Efficient Exploration Is Enough","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2610.03604","title":"Mastering Atari 2600 Games with Discovered Options","created":"2026-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2610.07686","title":"BluffJAX: Adversarial Imperfect Information Games in JAX","created":"2026-10-06","cited_by_count":0,"area":"deeprl"},{"id":"2610.13002","title":"Scaling Empowered Agents","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}