Towards Interpretable Reinforcement Learning Using Attention Augmented Agents
Alexander Mott, Daniel Zoran, Mike Chrzanowski, Daan Wierstra, Danilo Jimenez Rezende
Abstract
Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain. This model bottlenecks the view of an agent by a soft, top-down attention mechanism, forcing the agent to focus on task-relevant information by sequentially querying its view of the environment. The output of the attention mechanism allows direct observation of the information used by the agent to select its actions, enabling easier interpretation of this model than of traditional models. We analyze the different strategies the agents learn and show that a handful of strategies arise repeatedly across different games. We also show that the model learns to query separately about space and content (
BibTeX
@inproceedings{NEURIPS2019_e9510081,
author = {Mott, Alexander and Zoran, Daniel and Chrzanowski, Mike and Wierstra, Daan and Jimenez Rezende, Danilo},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Towards Interpretable Reinforcement Learning Using Attention Augmented Agents},
url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/e9510081ac30ffa83f10b68cde1cac07-Paper.pdf},
volume = {32},
year = {2019}
}