Benchmarking Perturbation-based Saliency Maps for Explaining Atari Agents

1 code implementation • 18 Jan 2021 • Tobias Huber, Benedikt Limmer, Elisabeth André

One of the most prominent methods for explaining the behavior of Deep Reinforcement Learning (DRL) agents is the generation of saliency maps that show how much each pixel attributed to the agents' decision.

Atari Games Benchmarking +2