{"total":359,"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":"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":"2505.22642","title":"FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control","created":"2025-05-28","cited_by_count":44,"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":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"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":"2405.13629","title":"Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow","created":"2024-05-22","cited_by_count":26,"area":"deeprl"},{"id":"2502.02133","title":"Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification","created":"2025-02-04","cited_by_count":26,"area":"deeprl"},{"id":"2405.15369","title":"Cross-Domain Policy Adaptation by Capturing Representation Mismatch","created":"2024-05-24","cited_by_count":25,"area":"deeprl"},{"id":"2410.20750","title":"ODRL: A Benchmark for Off-Dynamics Reinforcement Learning","created":"2024-10-28","cited_by_count":25,"area":"deeprl"},{"id":"2402.02868","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","created":"2024-02-05","cited_by_count":23,"area":"deeprl"},{"id":"2408.03029","title":"Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning","created":"2024-08-06","cited_by_count":22,"area":"deeprl"},{"id":"2405.17784","title":"Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation","created":"2024-05-28","cited_by_count":20,"area":"deeprl"},{"id":"2412.12089","title":"Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation","created":"2024-12-16","cited_by_count":20,"area":"deeprl"},{"id":"2410.09536","title":"TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning","created":"2024-10-12","cited_by_count":19,"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":"2405.00987","title":"S$^2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic","created":"2024-05-02","cited_by_count":18,"area":"deeprl"},{"id":"2405.19014","title":"Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption","created":"2024-05-29","cited_by_count":18,"area":"deeprl"},{"id":"2407.19396","title":"NAVIX: Scaling MiniGrid Environments with JAX","created":"2024-07-28","cited_by_count":18,"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":"2410.01312","title":"Sampling from Energy-based Policies using Diffusion","created":"2024-10-02","cited_by_count":17,"area":"deeprl"},{"id":"2501.17827","title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning","created":"2025-01-29","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":"2407.09645","title":"Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey","created":"2024-07-12","cited_by_count":16,"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":"2512.01996","title":"Learning Sim-to-Real Humanoid Locomotion in 15 Minutes","created":"2025-12-01","cited_by_count":16,"area":"deeprl"},{"id":"2404.09080","title":"Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications","created":"2024-04-13","cited_by_count":15,"area":"deeprl"},{"id":"2406.12563","title":"A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismo","created":"2024-06-18","cited_by_count":15,"area":"deeprl"},{"id":"2410.22600","title":"Solving Minimum-Cost Reach Avoid using Reinforcement Learning","created":"2024-10-29","cited_by_count":14,"area":"deeprl"},{"id":"2403.09930","title":"Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics","created":"2024-03-15","cited_by_count":13,"area":"deeprl"},{"id":"2411.02623","title":"Learning to Assist Humans without Inferring Rewards","created":"2024-11-04","cited_by_count":13,"area":"deeprl"},{"id":"2508.11143","title":"Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward","created":"2025-08-15","cited_by_count":13,"area":"deeprl"},{"id":"2401.11437","title":"Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning","created":"2024-01-21","cited_by_count":12,"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":"2407.11472","title":"DynSyn: Dynamical Synergistic Representation for Efficient Learning and Control in Overactuated Embodied Systems","created":"2024-07-16","cited_by_count":12,"area":"deeprl"},{"id":"2505.19850","title":"DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning","created":"2025-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2403.02290","title":"Koopman-Assisted Reinforcement Learning","created":"2024-03-04","cited_by_count":11,"area":"deeprl"},{"id":"2402.03141","title":"Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays","created":"2024-02-05","cited_by_count":10,"area":"deeprl"},{"id":"2405.18520","title":"Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL","created":"2024-05-28","cited_by_count":10,"area":"deeprl"},{"id":"2405.19697","title":"Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity","created":"2024-05-30","cited_by_count":10,"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":"2501.16918","title":"On Rollouts in Model-Based Reinforcement Learning","created":"2025-01-28","cited_by_count":10,"area":"deeprl"},{"id":"2405.11982","title":"Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space","created":"2024-05-20","cited_by_count":9,"area":"deeprl"},{"id":"2406.15131","title":"KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty","created":"2024-06-21","cited_by_count":9,"area":"deeprl"},{"id":"2411.04225","title":"Approximate Equivariance in Reinforcement Learning","created":"2024-11-06","cited_by_count":9,"area":"deeprl"},{"id":"2411.05614","title":"Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey","created":"2024-11-08","cited_by_count":8,"area":"deeprl"},{"id":"2509.23711","title":"Deterministic Policy Gradient for Reinforcement Learning with Continuous Time and State","created":"2025-09-28","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":"2405.18100","title":"A Pontryagin Perspective on Reinforcement Learning","created":"2024-05-28","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":"2407.07364","title":"Real-time system optimal traffic routing under uncertainties -- Can physics models boost reinforcement learning?","created":"2024-07-10","cited_by_count":7,"area":"deeprl"},{"id":"2408.09495","title":"Directed Exploration in Reinforcement Learning from Linear Temporal Logic","created":"2024-08-18","cited_by_count":7,"area":"deeprl"},{"id":"2409.13867","title":"MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safety","created":"2024-09-20","cited_by_count":7,"area":"deeprl"},{"id":"2503.23478","title":"Handling Delay in Real-Time Reinforcement Learning","created":"2025-03-30","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":"2506.04147","title":"SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Training","created":"2025-06-04","cited_by_count":7,"area":"deeprl"},{"id":"2506.05615","title":"When Maximum Entropy Misleads Policy Optimization","created":"2025-06-05","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":"2511.20066","title":"SOMBRL: Scalable and Optimistic Model-Based RL","created":"2025-11-25","cited_by_count":7,"area":"deeprl"},{"id":"2401.01084","title":"Global Convergence of Natural Policy Gradient with Hessian-aided Momentum Variance Reduction","created":"2024-01-02","cited_by_count":6,"area":"deeprl"},{"id":"2402.09992","title":"Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts","created":"2024-02-15","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":"2406.03995","title":"AC4MPC: Actor-Critic Reinforcement Learning for Nonlinear Model Predictive Control","created":"2024-06-06","cited_by_count":6,"area":"deeprl"},{"id":"2408.01972","title":"RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning","created":"2024-08-04","cited_by_count":6,"area":"deeprl"},{"id":"2410.04553","title":"Bisimulation metric for Model Predictive Control","created":"2024-10-06","cited_by_count":6,"area":"deeprl"},{"id":"2501.09080","title":"Average-Reward Soft Actor-Critic","created":"2025-01-15","cited_by_count":6,"area":"deeprl"},{"id":"2606.30376","title":"FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification","created":"2026-06-29","cited_by_count":6,"area":"deeprl"},{"id":"2401.09286","title":"Deployable Reinforcement Learning with Variable Control Rate","created":"2024-01-17","cited_by_count":5,"area":"deeprl"},{"id":"2402.02701","title":"Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence","created":"2024-02-05","cited_by_count":5,"area":"deeprl"},{"id":"2403.17845","title":"TractOracle: towards an anatomically-informed reward function for RL-based tractography","created":"2024-03-26","cited_by_count":5,"area":"deeprl"},{"id":"2405.12800","title":"Deep Reinforcement Learning for Time-Critical Wilderness Search And Rescue Using Drones","created":"2024-05-21","cited_by_count":5,"area":"deeprl"},{"id":"2408.03768","title":"HDPlanner: Advancing Autonomous Deployments in Unknown Environments through Hierarchical Decision Networks","created":"2024-08-07","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":"2502.20265","title":"On the Importance of Reward Design in Reinforcement Learning-based Dynamic Algorithm Configuration: A Case Study on OneMax with (1+($\\lambda$,$\\lambda$))-GA","created":"2025-02-27","cited_by_count":5,"area":"deeprl"},{"id":"2505.15143","title":"Filtering Learning Histories Enhances In-Context Reinforcement Learning","created":"2025-05-21","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":"2509.00215","title":"First Order Model-Based RL through Decoupled Backpropagation","created":"2025-08-29","cited_by_count":5,"area":"deeprl"},{"id":"2601.15353","title":"Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions","created":"2026-01-21","cited_by_count":5,"area":"deeprl"},{"id":"2401.14858","title":"RESPRECT: Speeding-up Multi-fingered Grasping with Residual Reinforcement Learning","created":"2024-01-26","cited_by_count":4,"area":"deeprl"},{"id":"2402.03055","title":"Deep Exploration with PAC-Bayes","created":"2024-02-05","cited_by_count":4,"area":"deeprl"},{"id":"2402.13930","title":"Enhancing Reinforcement Learning Agents with Local Guides","created":"2024-02-21","cited_by_count":4,"area":"deeprl"},{"id":"2402.15197","title":"Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization","created":"2024-02-23","cited_by_count":4,"area":"deeprl"},{"id":"2407.18143","title":"Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation","created":"2024-07-25","cited_by_count":4,"area":"deeprl"},{"id":"2412.02291","title":"Conformal Symplectic Optimization for Stable Reinforcement Learning","created":"2024-12-03","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":"2507.11060","title":"Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing","created":"2025-07-15","cited_by_count":4,"area":"deeprl"},{"id":"2508.20784","title":"Single Agent Robust Deep Reinforcement Learning for Bus Fleet Control","created":"2025-08-28","cited_by_count":4,"area":"deeprl"},{"id":"2401.10516","title":"Episodic Reinforcement Learning with Expanded State-reward Space","created":"2024-01-19","cited_by_count":3,"area":"deeprl"},{"id":"2401.13148","title":"Stable and Safe Human-aligned Reinforcement Learning through Neural Ordinary Differential Equations","created":"2024-01-23","cited_by_count":3,"area":"deeprl"},{"id":"2402.00162","title":"Behind the Myth of Exploration in Policy Gradients","created":"2024-01-31","cited_by_count":3,"area":"deeprl"},{"id":"2402.10374","title":"Revisiting Experience Replayable Conditions","created":"2024-02-15","cited_by_count":3,"area":"deeprl"},{"id":"2402.14961","title":"Reinforcement Learning with Elastic Time Steps","created":"2024-02-22","cited_by_count":3,"area":"deeprl"},{"id":"2403.04162","title":"Noisy Spiking Actor Network for Exploration","created":"2024-03-07","cited_by_count":3,"area":"deeprl"},{"id":"2403.12210","title":"Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning","created":"2024-03-18","cited_by_count":3,"area":"deeprl"},{"id":"2406.12589","title":"Discovering Minimal Reinforcement Learning Environments","created":"2024-06-18","cited_by_count":3,"area":"deeprl"},{"id":"2407.21338","title":"Image-Based Deep Reinforcement Learning with Intrinsically Motivated Stimuli: On the Execution of Complex Robotic Tasks","created":"2024-07-31","cited_by_count":3,"area":"deeprl"},{"id":"2408.07962","title":"Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuning","created":"2024-08-15","cited_by_count":3,"area":"deeprl"},{"id":"2408.14747","title":"Benchmarking Reinforcement Learning Methods for Dexterous Robotic Manipulation with a Three-Fingered Gripper","created":"2024-08-27","cited_by_count":3,"area":"deeprl"}],"next_cursor":"100"}