{"total":17,"rows":[{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176,"area":"deeprl"},{"id":"2506.05997","title":"Spatially-Enhanced Recurrent Memory for Long-Range Mapless Navigation via End-to-End Reinforcement Learning","created":"2025-06-06","cited_by_count":11,"area":"deeprl"},{"id":"2503.08299","title":"Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotion","created":"2025-03-11","cited_by_count":10,"area":"deeprl"},{"id":"2406.04835","title":"SLR: Learning Quadruped Locomotion without Privileged Information","created":"2024-06-07","cited_by_count":6,"area":"deeprl"},{"id":"2409.19709","title":"DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multi-Modal Reinforcement Learning","created":"2024-09-29","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":"2410.17551","title":"Multimodal Information Bottleneck for Deep Reinforcement Learning with Multiple Sensors","created":"2024-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2508.19153","title":"QuadKAN: KAN-Enhanced Quadruped Motion Control via End-to-End Reinforcement Learning","created":"2025-08-26","cited_by_count":2,"area":"deeprl"},{"id":"2509.09106","title":"LIPM-Guided Reinforcement Learning for Stable and Perceptive Locomotion in Bipedal Robots","created":"2025-09-11","cited_by_count":2,"area":"deeprl"},{"id":"2602.00678","title":"Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion","created":"2026-01-31","cited_by_count":2,"area":"deeprl"},{"id":"2405.11457","title":"Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice","created":"2024-05-19","cited_by_count":1,"area":"deeprl"},{"id":"2506.20036","title":"Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotion","created":"2025-06-24","cited_by_count":1,"area":"deeprl"},{"id":"2606.00637","title":"Global-Local Attention Decomposition for Terrain Encoding in Humanoid Perceptive Locomotion","created":"2026-05-30","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":"2503.04462","title":"PALo: Learning Posture-Aware Locomotion for Quadruped Robots","created":"2025-03-06","cited_by_count":0,"area":"deeprl"},{"id":"2510.14338","title":"Risk-Aware Reinforcement Learning with Bandit-Based Adaptation for Quadrupedal Locomotion","created":"2025-10-16","cited_by_count":0,"area":"deeprl"},{"id":"2606.31320","title":"Safe Online Learning via Smooth Safety-Structured Policy Composition","created":"2026-06-30","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}