Regret Bounds for Risk-Sensitive Reinforcement Learning

no code implementations • 11 Oct 2022 • O. Bastani, Y. J. Ma, E. Shen, W. Xu

In safety-critical applications of reinforcement learning such as healthcare and robotics, it is often desirable to optimize risk-sensitive objectives that account for tail outcomes rather than expected reward.

reinforcement-learning Reinforcement Learning (RL)