Adapting to Unseen Environments through Explicit Representation of Context (2020)
In order to deploy autonomous agents to domains such as autonomous driving, infrastructure management, health care, and finance, they must be able to adapt safely to unseen situations. The current approach in constructing such agents is to try to include as much variation into training as possible, and then generalize within the possible variations. This paper proposes a principled approach where a context module is coevolved with a skill module. The context module recognizes the variation and modulates the skill module so that the entire system performs well in unseen situations. The approach is evaluated in a challenging version of the Flappy Bird game where the effects of the actions vary over time. The Context+Skill approach leads to significantly more robust behavior in environments with previously unseen effects. Such a principled generalization ability is essential in deploying autonomous agents in real world tasks, and can serve as a foundation for continual learning as well.
View:
PDF
Citation:
In Proceedings of the 2020 Conference on Artificial Life (ALIFE 2020), 581--588, Montreal, Canada, July 2020. The MIT Press.
Bibtex:

Presentation:
Video
Risto Miikkulainen Faculty risto [at] cs utexas edu
Cem C Tutum Research Scientist tutum [at] cs utexas edu