Lifelong Learning with a Changing Action Set
It addresses an unaddressed setting in lifelong learning for sequential decision-making problems, though it appears incremental as it builds on existing lifelong learning concepts.
The paper tackles the problem of lifelong learning with a changing action set, where the number of available actions varies over time, by proposing an algorithm that infers action structure and optimizes policies iteratively, demonstrating efficiency on large-scale real-world problems.
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.