{"total":98,"rows":[{"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":"2407.17032","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","created":"2024-07-24","cited_by_count":46,"area":"deeprl"},{"id":"2402.17257","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","created":"2024-02-27","cited_by_count":39,"area":"deeprl"},{"id":"2502.13187","title":"A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models","created":"2025-02-18","cited_by_count":38,"area":"deeprl"},{"id":"2502.10550","title":"Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning","created":"2025-02-14","cited_by_count":36,"area":"deeprl"},{"id":"2509.25756","title":"SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling","created":"2025-09-30","cited_by_count":31,"area":"deeprl"},{"id":"2403.09110","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","created":"2024-03-14","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":"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":"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":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13,"area":"deeprl"},{"id":"2502.19652","title":"Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning","created":"2025-02-27","cited_by_count":13,"area":"deeprl"},{"id":"2505.00663","title":"Wasserstein Policy Optimization","created":"2025-05-01","cited_by_count":13,"area":"deeprl"},{"id":"2403.10940","title":"ViSaRL: Visual Reinforcement Learning Guided by Human Saliency","created":"2024-03-16","cited_by_count":12,"area":"deeprl"},{"id":"2411.12155","title":"Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning","created":"2024-11-19","cited_by_count":10,"area":"deeprl"},{"id":"2407.01903","title":"Text-Aware Diffusion for Policy Learning","created":"2024-07-02","cited_by_count":8,"area":"deeprl"},{"id":"2404.04253","title":"Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution","created":"2024-04-05","cited_by_count":7,"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":"2406.01423","title":"Value Improved Actor Critic Algorithms","created":"2024-06-03","cited_by_count":7,"area":"deeprl"},{"id":"2410.08870","title":"Can we hop in general? A discussion of benchmark selection and design using the Hopper environment","created":"2024-10-11","cited_by_count":7,"area":"deeprl"},{"id":"2401.08850","title":"REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes","created":"2024-01-16","cited_by_count":6,"area":"deeprl"},{"id":"2502.17322","title":"TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Control","created":"2025-02-24","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":"2401.06604","title":"Identifying Policy Gradient Subspaces","created":"2024-01-12","cited_by_count":5,"area":"deeprl"},{"id":"2406.16255","title":"Uncertainty-Aware Reward-Free Exploration with General Function Approximation","created":"2024-06-24","cited_by_count":5,"area":"deeprl"},{"id":"2409.16824","title":"Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability","created":"2024-09-25","cited_by_count":5,"area":"deeprl"},{"id":"2505.19247","title":"Improving Value Estimation Critically Enhances Vanilla Policy Gradient","created":"2025-05-25","cited_by_count":5,"area":"deeprl"},{"id":"2509.01765","title":"Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control","created":"2025-09-01","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":"2401.06514","title":"Personalized Reinforcement Learning with a Budget of Policies","created":"2024-01-12","cited_by_count":4,"area":"deeprl"},{"id":"2407.18841","title":"QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-Learning","created":"2024-07-26","cited_by_count":4,"area":"deeprl"},{"id":"2408.00309","title":"Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning","created":"2024-08-01","cited_by_count":4,"area":"deeprl"},{"id":"2410.06621","title":"Effective Exploration Based on the Structural Information Principles","created":"2024-10-09","cited_by_count":4,"area":"deeprl"},{"id":"2410.10674","title":"Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach","created":"2024-10-14","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":"2506.01016","title":"Optimistic critics can empower small actors","created":"2025-06-01","cited_by_count":4,"area":"deeprl"},{"id":"2510.17122","title":"Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control","created":"2025-10-20","cited_by_count":4,"area":"deeprl"},{"id":"2402.10374","title":"Revisiting Experience Replayable Conditions","created":"2024-02-15","cited_by_count":3,"area":"deeprl"},{"id":"2407.03995","title":"ROER: Regularized Optimal Experience Replay","created":"2024-07-04","cited_by_count":3,"area":"deeprl"},{"id":"2411.06174","title":"State Chrono Representation for Enhancing Generalization in Reinforcement Learning","created":"2024-11-09","cited_by_count":3,"area":"deeprl"},{"id":"2506.00138","title":"Intrinsic Goals for Autonomous Agents: Model-Based Exploration in Virtual Zebrafish Predicts Ethological Behavior and Whole-Brain Dynamics","created":"2025-05-30","cited_by_count":3,"area":"deeprl"},{"id":"2506.21044","title":"Efficient Skill Discovery via Regret-Aware Optimization","created":"2025-06-26","cited_by_count":3,"area":"deeprl"},{"id":"2507.20853","title":"Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces","created":"2025-07-28","cited_by_count":3,"area":"deeprl"},{"id":"2510.24482","title":"Sample-efficient and Scalable Exploration in Continuous-Time RL","created":"2025-10-28","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":"2603.06413","title":"A Reference Architecture of Reinforcement Learning Frameworks","created":"2026-03-06","cited_by_count":3,"area":"deeprl"},{"id":"2605.30749","title":"FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance","created":"2026-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2402.12034","title":"When Do Off-Policy and On-Policy Policy Gradient Methods Align?","created":"2024-02-19","cited_by_count":2,"area":"deeprl"},{"id":"2404.17687","title":"Knowledge Transfer for Cross-Domain Reinforcement Learning: A Systematic Review","created":"2024-04-26","cited_by_count":2,"area":"deeprl"},{"id":"2501.02620","title":"Back to Base: Towards Hands-Off Learning via Safe Resets with Reach-Avoid Safety Filters","created":"2025-01-05","cited_by_count":2,"area":"deeprl"},{"id":"2505.22772","title":"Calibrated Value-Aware Model Learning with Probabilistic Environment Models","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2506.21782","title":"M3PO: Massively Multi-Task Model-Based Policy Optimization","created":"2025-06-26","cited_by_count":2,"area":"deeprl"},{"id":"2603.09237","title":"MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for Robotics","created":"2026-03-10","cited_by_count":2,"area":"deeprl"},{"id":"2402.13654","title":"Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark","created":"2024-02-21","cited_by_count":1,"area":"deeprl"},{"id":"2403.04453","title":"Efficient Off-Policy Learning for High-Dimensional Action Spaces","created":"2024-03-07","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":"2405.16739","title":"Oracle-Efficient Reinforcement Learning for Max Value Ensembles","created":"2024-05-27","cited_by_count":1,"area":"deeprl"},{"id":"2409.05433","title":"State-Novelty Guided Action Persistence in Deep Reinforcement Learning","created":"2024-09-09","cited_by_count":1,"area":"deeprl"},{"id":"2502.03854","title":"Mirror Descent Actor Critic via Bounded Advantage Learning","created":"2025-02-06","cited_by_count":1,"area":"deeprl"},{"id":"2506.05968","title":"Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning","created":"2025-06-06","cited_by_count":1,"area":"deeprl"},{"id":"2512.06252","title":"Learning Without Time-Based Embodiment Resets in Soft-Actor Critic","created":"2025-12-06","cited_by_count":1,"area":"deeprl"},{"id":"2512.15439","title":"Double Horizon Model-Based Policy Optimization","created":"2025-12-17","cited_by_count":1,"area":"deeprl"},{"id":"2602.02098","title":"Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning","created":"2026-02-02","cited_by_count":1,"area":"deeprl"},{"id":"2604.05931","title":"Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning","created":"2026-04-07","cited_by_count":1,"area":"deeprl"},{"id":"2605.04568","title":"Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination","created":"2026-05-06","cited_by_count":1,"area":"deeprl"},{"id":"2605.08733","title":"Generative Actor-Critic with Soft Bridge Policies","created":"2026-05-09","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":"2606.18594","title":"Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation","created":"2026-06-17","cited_by_count":1,"area":"deeprl"},{"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":"2607.16534","title":"Building2Building: A Large Scale Benchmark for Generalizable Real-World Reinforcement Learning","created":"2026-07-17","cited_by_count":1,"area":"deeprl"},{"id":"2404.10645","title":"Continuous Control Reinforcement Learning: Distributed Distributional DrQ Algorithms","created":"2024-04-16","cited_by_count":0,"area":"deeprl"},{"id":"2408.13498","title":"Rethinking State Disentanglement in Causal Reinforcement Learning","created":"2024-08-24","cited_by_count":0,"area":"deeprl"},{"id":"2410.06847","title":"A Safety Modulator Actor-Critic Method in Model-Free Safe Reinforcement Learning and Application in UAV Hovering","created":"2024-10-09","cited_by_count":0,"area":"deeprl"},{"id":"2505.15754","title":"Improving planning and MBRL with temporally-extended actions","created":"2025-05-21","cited_by_count":0,"area":"deeprl"},{"id":"2506.16608","title":"Distributions as Actions: A Unified Framework for Diverse Action Spaces","created":"2025-06-19","cited_by_count":0,"area":"deeprl"},{"id":"2508.18817","title":"Learning Acrobatic Flight from Preferences","created":"2025-08-26","cited_by_count":0,"area":"deeprl"},{"id":"2509.22964","title":"Functional Critics Are Essential for Actor-Critic: From Off-Policy Stability to Efficient Exploration","created":"2025-09-26","cited_by_count":0,"area":"deeprl"},{"id":"2510.01457","title":"A Forensic Analysis of Synthetic Data in RL: Diagnosing and Solving Algorithmic Failures in Model-Based Policy Optimization","created":"2025-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2511.07904","title":"Test-driven Reinforcement Learning in Continuous Control","created":"2025-11-11","cited_by_count":0,"area":"deeprl"},{"id":"2512.10492","title":"UACER: An Uncertainty-Adaptive Critic Ensemble Framework for Robust Adversarial Reinforcement Learning","created":"2025-12-11","cited_by_count":0,"area":"deeprl"},{"id":"2603.08588","title":"Towards Batch-to-Streaming Deep Reinforcement Learning for Continuous Control","created":"2026-03-09","cited_by_count":0,"area":"deeprl"},{"id":"2604.23312","title":"GIFT: Global stabilisation via Intrinsic Fine Tuning","created":"2026-04-25","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":"2605.12312","title":"Transferable Delay-Aware Reinforcement Learning via Implicit Causal Graph Modeling","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.14026","title":"R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2605.23415","title":"Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2606.03201","title":"Reinforcement Learning from Cross-domain Videos with Video Prediction Model","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2607.01880","title":"Learning the Supports for Categorical Critic in Reinforcement Learning","created":"2026-07-02","cited_by_count":0,"area":"deeprl"},{"id":"2607.17326","title":"Rethinking the Suitability of Reinforcement Learning Algorithms Under Practical Transfer Constraints","created":"2026-07-19","cited_by_count":0,"area":"deeprl"},{"id":"2609.27667","title":"Robust Adversarial Reinforcement Learning with Risk Sensitivity and Critic Consistency Regularization","created":"2026-09-23","cited_by_count":0,"area":"deeprl"},{"id":"2609.30570","title":"MOCHA: Multi-Objective Co-Design using Hypernetwork Architectures","created":"2026-09-24","cited_by_count":0,"area":"deeprl"},{"id":"2610.01566","title":"Towards Optimal Policy Improvement","created":"2026-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.02012","title":"Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering Chaos","created":"2026-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.06019","title":"Adaptive Expert Guidance for Efficient On-Policy Reinforcement Learning","created":"2026-10-05","cited_by_count":0,"area":"deeprl"},{"id":"2610.14400","title":"Sparse-TD-JEPA: Improving Zero-Shot Reinforcement Learning With Sparse Latent Task Representations","created":"2026-10-09","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}