Adapting to Unseen Environments through Explicit Representation of Context
This addresses the need for safe adaptation in real-world domains like autonomous driving and healthcare, though it appears incremental as it builds on existing modular methods.
The paper tackles the problem of enabling autonomous agents to adapt to unseen environments by proposing a Context+Skill approach, where a context module recognizes variations and modulates a skill module, resulting in significantly more robust behavior in a challenging Flappy Bird game with previously unseen effects.
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.