Lifelong Learning with a Changing Action Set

Thirty-fourth Conference on Artificial Intelligence (AAAI 2020)

Published February 7, 2020

Yash Chandak, Georgios Theocharous, Chris Nota, Philip S.Thomas

Outstanding Student Paper Honorable Mention

In many real-world sequential decision making problems, the number of available actions (decisions) can vary over time. While problems like catastrophic forgetting, changing transition dynamics, changing rewards functions, etc. have been well-studied in the lifelong learning literature, the setting where the action set changes remains unaddressed. In this paper, we present an algorithm that autonomously adapts to an action set whose size changes over time. To tackle this open problem, we break it into two problems that can be solved iteratively: inferring the underlying, unknown, structure in the space of actions and optimizing a policy that leverages this structure. We demonstrate the efficiency of this approach on large-scale real-world lifelong learning problems.

Learn More

Research Area:  AI & Machine Learning