Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety

3 code implementations • 22 May 2021 • Haitong Ma, Yang Guan, Shegnbo Eben Li, Xiangteng Zhang, Sifa Zheng, Jianyu Chen

The safety constraints commonly used by existing safe reinforcement learning (RL) methods are defined only on expectation of initial states, but allow each certain state to be unsafe, which is unsatisfying for real-world safety-critical tasks.

reinforcement-learning Reinforcement Learning (RL) +2