10 papers
AgilePE: Autonomous UAV Pursuit-Evasion via Self-Play Reinforcement Learning
Wenhao Tang, Tianyang Chen, Zhejun Cui +9
Autonomous pursuit-evasion is a fundamental challenge for Unmanned Aerial Vehicles (UAVs), requiring rapid decision-making under tightly coupled dynamics and continuously changing…
What Can RL Bring to VLA Generalization? An Empirical Study
Jijia Liu, Feng Gao, Bingwen Wei +5
Large Vision-Language Action (VLA) models have shown significant potential for embodied AI. However, their predominant training via supervised fine-tuning (SFT) limits generalizati…
Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance
Songsheng Wang, Rucheng Yu, Zhihang Yuan +4
Vision-Language-Action (VLA) models have made substantial progress by leveraging the robust capabilities of Visual Language Models (VLMs). However, VLMs' significant parameter size…
D3P: Dynamic Denoising Diffusion Policy via Reinforcement Learning
Shu-Ang Yu, Feng Gao, Yi Wu +2
Diffusion policies excel at learning complex action distributions for robotic visuomotor tasks, yet their iterative denoising process poses a major bottleneck for real-time deploym…
Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network
Jijia Liu, Feng Gao, Qingmin Liao +2
Reinforcement learning (RL) for continuous control often requires large amounts of online interaction data. Value-based RL methods can mitigate this burden by offering relatively h…
What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Study
Jiayu Chen, Chao Yu, Yuqing Xie +9
Executing precise and agile flight maneuvers is critical for quadrotors in various applications. Traditional quadrotor control approaches are limited by their reliance on flat traj…