{"total":15,"rows":[{"id":"2405.02425","title":"Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning","created":"2024-05-03","cited_by_count":17,"area":"deeprl"},{"id":"2504.17857","title":"High-Performance Reinforcement Learning on Spot: Optimizing Simulation Parameters with Distributional Measures","created":"2025-04-24","cited_by_count":10,"area":"deeprl"},{"id":"2403.12193","title":"Continual Domain Randomization","created":"2024-03-18","cited_by_count":8,"area":"deeprl"},{"id":"2604.02523","title":"Tune to Learn: How Controller Gains Shape Robot Policy Learning","created":"2026-04-02","cited_by_count":8,"area":"deeprl"},{"id":"2503.24371","title":"Policy Gradient for LQR with Domain Randomization","created":"2025-03-31","cited_by_count":5,"area":"deeprl"},{"id":"2503.10949","title":"Safe Continual Domain Adaptation after Sim2Real Transfer of Reinforcement Learning Policies in Robotics","created":"2025-03-13","cited_by_count":2,"area":"deeprl"},{"id":"2504.15414","title":"Post-Convergence Sim-to-Real Policy Transfer: A Principled Alternative to Cherry-Picking","created":"2025-04-21","cited_by_count":1,"area":"deeprl"},{"id":"2507.03068","title":"Mitigating Goal Misgeneralization via Minimax Regret","created":"2025-07-03","cited_by_count":1,"area":"deeprl"},{"id":"2510.25063","title":"Control Synthesis with Reinforcement Learning: A Modeling Perspective","created":"2025-10-29","cited_by_count":1,"area":"deeprl"},{"id":"2412.13224","title":"Physics-model-guided Worst-case Sampling for Safe Reinforcement Learning","created":"2024-12-17","cited_by_count":0,"area":"deeprl"},{"id":"2602.06326","title":"Online Adaptive Reinforcement Learning with Echo State Networks for Non-Stationary Dynamics","created":"2026-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2606.22145","title":"Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System","created":"2026-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2607.11959","title":"Calibration-First Reward-Component Auditing for Reinforcement Learning Control in Smart Greenhouses","created":"2026-07-12","cited_by_count":0,"area":"deeprl"},{"id":"2610.06400","title":"Visual Swarm Navigation via Deep Reinforcement Learning and Evolutionary Hybrid Design","created":"2026-10-05","cited_by_count":0,"area":"deeprl"},{"id":"2610.16478","title":"XAI-Guided Fourier Domain Generalisation for Pure-Simulation Sim-to-Real Deep Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}