Explaining Reinforcement Learning: A Survey

Authors: P. He, K. Y. K. Lui, et al.
Year: 2023
Summary: This survey provides a comprehensive overview of methods for explaining the policies of reinforcement learning (RL) agents. It categorizes techniques for explaining why an agent chose a particular action, what it is trying to achieve, and how its policy works. This is essential for understanding and trusting autonomous agents that learn from experience.
Link: https://arxiv.org/abs/2305.15623