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.
CITATION STYLE
Weitkamp, L., van der Pol, E., & Akata, Z. (2019). Visual Rationalizations in Deep Reinforcement Learning for Atari Games. In Communications in Computer and Information Science (Vol. 1021, pp. 151–165). Springer. https://doi.org/10.1007/978-3-030-31978-6_12
Mendeley helps you to discover research relevant for your work.