Self-Explaining Deviations for Coordination
Abstract
Fully cooperative, partially observable multi-agent problems are ubiquitous in the real world. In this paper, we focus on a specific subclass of coordination problems in which humans are able to discover self-explaining deviations (SEDs). SEDs are actions that deviate from the common understanding of what reasonable behavior would be in normal circumstances. They are taken with the intention of causing another agent or other agents to realize, using theory of mind, that the circumstance must be abnormal. We motivate this idea with a real world example and formalize its definition. Next, we introduce an algorithm for improvement maximizing SEDs (IMPROVISED). Lastly, we evaluate IMPROVISED both in an illustrative toy setting and the popular benchmark setting Hanabi, where we show that it can produce so called finesse plays.
Cite
Text
Hu et al. "Self-Explaining Deviations for Coordination." Neural Information Processing Systems, 2022.Markdown
[Hu et al. "Self-Explaining Deviations for Coordination." Neural Information Processing Systems, 2022.](https://mlanthology.org/neurips/2022/hu2022neurips-selfexplaining/)BibTeX
@inproceedings{hu2022neurips-selfexplaining,
title = {{Self-Explaining Deviations for Coordination}},
author = {Hu, Hengyuan and Sokota, Samuel and Wu, David and Bakhtin, Anton and Lupu, Andrei and Cui, Brandon and Foerster, Jakob},
booktitle = {Neural Information Processing Systems},
year = {2022},
url = {https://mlanthology.org/neurips/2022/hu2022neurips-selfexplaining/}
}