Learning reliably safe autonomous control is one of the core problems in trustworthy autonomy.

Reinforcement learning (RL) studies the problem where an agent interacts with an unknown environment to optimize cumulative rewards/losses [Sutton and Barto, 2018].

With the success of deep learning, there are growing concerns over interpretability (Lipton, 2018). Ideally, the explanation should be both faithful (reflecting the model's actual behavior) and plausible

The softmax function is ubiquitous in machine learning and optimization applications.

It is common to assess a model's merit for scientific discovery, and thus novel insights, by how well it aligns with already available domain