We introduce the Blackwell discount factor for Markov Decision Processes (MDPs). Classical objectives for MDPs include discounted, average, and Blackwell opti-mality.

While being straightforward, this result seems new for GDRO.

Risk-averse reinforcement learning (RL) seeks to provide a risk-averse policy for high-stakes real-world decision problems. These high-stake domains include autonomous driving (Jin et al., 2019; Sharma et al., 2020), robot collision avoidance (Ahmadi et al., 2021; Hakobyan and Y ang, 2021),