PapersBuilders73°11:41Chinese contentCAST结合规划器引导行为提升强化学习新提出的CAST方法结合规划器与策略,在强化学习中实现更高效的值学习,并在四足机器人上验证效果。#CAST#reinforcement learning#quadruped robotsaarXiv: Google DeepMind@Pietro Noah Crestaz et al. (4)SourceRead laterReadWorth followingUsefulFollow CAST