LOCOMOTION
弥合差距:实现高性能腿式运动的软演员-评论家算法
Gianluca Sabatini, Chenhao Li, Marco Hutter
- 发表年份
- 2026
- 访问权限
- 开放获取
摘要
本文揭示了软演员-评论家(SAC)算法在大规模并行训练中性能不如近端策略优化(PPO)的根本原因,并提出了策略初始化、超时感知评论家目标及多步回报估计等针对性改进,使得SAC在多种腿式机器人平台上完全弥合了与PPO的性能差距。
关键词
Soft Actor-Criticlegged locomotionsim-to-realsample efficiencyreinforcement learning
相关论文
LOCOMOTION
开放获取📊 3,141 引用
Trust Region Policy Optimization
John Schulman, Sergey Levine, Philipp Moritz 等 5 位作者
2015
LOCOMOTION
📊 2,724 引用
Legged Robots That Balance
Marc H. Raibert, Ernest R. Tello
1986
LOCOMOTION
📊 2,658 引用
Being there: putting brain, body, and world together again
1997
LOCOMOTION
📊 2,305 引用
Small-scale soft-bodied robot with multimodal locomotion
Wenqi Hu, Guo Zhan Lum, Massimo Mastrangeli 等 4 位作者
2018