Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks
It addresses the problem of specifying tasks for AI agents in a more efficient and adaptable way, but is incremental as it surveys existing methods rather than introducing new ones.
This survey reviews five recent machine learning frameworks that use human guidance beyond traditional reward functions or demonstrations for sequential decision-making tasks, aiming to reduce human effort and improve suitability for certain tasks.
A longstanding goal of artificial intelligence is to create artificial agents capable of learning to perform tasks that require sequential decision making. Importantly, while it is the artificial agent that learns and acts, it is still up to humans to specify the particular task to be performed. Classical task-specification approaches typically involve humans providing stationary reward functions or explicit demonstrations of the desired tasks. However, there has recently been a great deal of research energy invested in exploring alternative ways in which humans may guide learning agents that may, e.g., be more suitable for certain tasks or require less human effort. This survey provides a high-level overview of five recent machine learning frameworks that primarily rely on human guidance apart from pre-specified reward functions or conventional, step-by-step action demonstrations. We review the motivation, assumptions, and implementation of each framework, and we discuss possible future research directions.