In this paper, we provide an overview of the existing methods for integrating human advice into a reinforcement learning process. We first propose a taxonomy of the different forms of advice that can be provided to a learning agent. We then describe the methods that can be used for interpreting advice when its meaning is not determined beforehand. Finally, we review different approaches for integrating advice into the learning process.
CITATION STYLE
Najar, A., & Chetouani, M. (2021, June 1). Reinforcement Learning With Human Advice: A Survey. Frontiers in Robotics and AI. Frontiers Media S.A. https://doi.org/10.3389/frobt.2021.584075
Mendeley helps you to discover research relevant for your work.