User-Oriented Robust Reinforcement Learning

no code implementations • 15 Feb 2022 • Haoyi You, Beichen Yu, Haiming Jin, Zhaoxing Yang, Jiahui Sun

Specifically, we define a new User-Oriented Robustness (UOR) metric for RL, which allocates different weights to the environments according to user preference and generalizes the max-min robustness metric.

reinforcement-learning Reinforcement Learning (RL)