Reinforcement Learning With Human Advice: A Survey
Anis Najar, Mohamed Chétouani · Frontiers in Robotics and AI · 2021
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.