We argue that these properties are satisfied in many continuous state-action Markov decision processes.

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),

As the learned attention mechanisms tend to use few of these edges, such high-degree connections may be unnecessary.

Recent works along these lines learn task-dependent regularizers.