Visual Rationalizations in Deep Reinforcement Learning for Atari Games
Machine Learning
2019-02-05 v1 Machine Learning
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.
Cite
@article{arxiv.1902.00566,
title = {Visual Rationalizations in Deep Reinforcement Learning for Atari Games},
author = {Laurens Weitkamp and Elise van der Pol and Zeynep Akata},
journal= {arXiv preprint arXiv:1902.00566},
year = {2019}
}
Comments
presented as oral talk at BNAIC 2018