Published on Fri Feb 01 2019

Visual Rationalizations in Deep Reinforcement Learning for Atari Games

Laurens Weitkamp, Elise van der Pol, Zeynep Akata

Deep reinforcement learning agents perform well in challenging tasks such as Atari 2600 games. However, clearly explaining why a certain action is taken can be as important as the decision itself. In this work, we emphasize the importance of producing a justification for an observed action.

0
0
0
Abstract

Due to the capability of deep learning to perform well in high dimensional problems, deep reinforcement learning agents perform well in challenging tasks such as Atari 2600 games. However, clearly explaining why a certain action is taken by the agent can be as important as the decision itself. Deep reinforcement learning models, as other deep learning models, tend to be opaque in their decision-making process. In this work, we propose to make deep reinforcement learning more transparent by visualizing the evidence on which the agent bases its decision. In this work, we emphasize the importance of producing a justification for an observed action, which could be applied to a black-box decision agent.