Visualizing and Understanding Atari Agents


Deep reinforcement learning (deep RL) agents have achieved remarkable success in a broad range of game-playing and continuous control tasks. While these agents are effective at maximizing rewards, it is often unclear what strategies they use to do so. In this paper, we take a step toward explaining deep RL agents through a case study in three Atari 2600… (More)


6 Figures and Tables

Cite this paper

@article{Greydanus2017VisualizingAU, title={Visualizing and Understanding Atari Agents}, author={Sam Greydanus and Anurag Koul and Jonathan Dodge and Alan Fern}, journal={CoRR}, year={2017}, volume={abs/1711.00138} }