PapersBuilders10:26Chinese contentFERPO:前熵正则化策略优化算法新提出的FERPO算法解决了传统强化学习中critic值预测不准确的问题,在连续控制任务中表现优异。#FERPO#reinforcement learning#policy optimization#entropy regularizationaarXiv cs.LG@Sebastian Sanokowski et al. (3)SourceRead laterReadWorth followingUsefulFollow FERPO