发帖
雷达卡
Safe Reinforcement Learning with Linear Function Approximation
Sanae Amani 1 Christos Thrampoulidis 2 Lin F. Yang 1
Abstract action may lead to catastrophic results. Thus, safety in RL
has become a serious issue that restricts the applicability of
Safety in reinforcement learning has become in- RL algorithms to many real-world systems. For example,
creasingly important in recent years. Yet, exist- in ...
京公网安备 11010802022788号
