在15分钟内学习仿真到现实的人形机器人运动控制
Learning Sim-to-Real Humanoid Locomotion in 15 Minutes
AI总结：
本研究提出了一种基于FastSAC和FastTD3的简单方法，在15分钟内通过单块RTX 4090 GPU实现人形机器人运动控制的快速训练。
摘要：
大规模并行仿真已经将强化学习（RL）训练时间从天数减少到分钟。然而，由于高维性和领域随机化等因素带来的挑战，实现快速且可靠的仿真到现实RL对于人形控制仍然困难。在本工作中，我们介绍了一种基于非策略RL算法（即FastSAC和FastTD3）的简单且实用的方法，该方法能够通过单块RTX 4090 GPU在15分钟内快速训练人形运动策略。我们的简单方法通过精心设计的调优选择和极简的奖励函数，在大规模并行环境中稳定了非策略RL算法。我们展示了在Unitree G1和Booster T1机器人上，在强领域随机化条件下（如随机动力学、粗糙地形和推扰）实现快速端到端学习人形运动控制器，并快速训练了全身人体运动跟踪策略。我们提供了视频和开源实现：https://younggyo.me/fastsac-humanoid。
英文摘要：
Massively parallel simulation has reduced reinforcement learning (RL) training time for robots from days to minutes. However, achieving fast and reliable sim-to-real RL for humanoid control remains difficult due to the challenges introduced by factors such as high dimensionality and domain randomization. In this work, we introduce a simple and practical recipe based on off-policy RL algorithms, i.e., FastSAC and FastTD3, that enables rapid training of humanoid locomotion policies in just 15 minutes with a single RTX 4090 GPU. Our simple recipe stabilizes off-policy RL algorithms at massive scale with thousands of parallel environments through carefully tuned design choices and minimalist reward functions. We demonstrate rapid end-to-end learning of humanoid locomotion controllers on Unitree G1 and Booster T1 robots under strong domain randomization, e.g., randomized dynamics, rough terrain, and push perturbations, as well as fast training of whole-body human-motion tracking policies. We provide videos and open-source implementation at: https://younggyo.me/fastsac-humanoid.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
