Read Entropy's High-cited Article "An Information-Theoretic Perspective on Intrinsic Motivation in Reinforcement Learning: A Survey"

Authors: Arthur Aubret, Laetitia Matignon and Salima Hassas

Read full article at: https://www.mdpi.com/1099-4300/25/2/327

Abstract: The reinforcement learning (RL) research area is very active, with an important number of new contributions, especially considering the emergent field of deep RL (DRL). However, a number of scientific and technical challenges still need to be resolved, among which we acknowledge the?ability to abstract actions?or?the difficulty to explore the environment in sparse-reward settings?which can be addressed by intrinsic motivation (IM). We propose to survey these research works through a new taxonomy based on information theory: we computationally revisit the notions of surprise, novelty, and skill-learning. This allows us to identify advantages and disadvantages of methods and exhibit current outlooks of research. Our analysis suggests that novelty and surprise can assist the building of a hierarchy of transferable skills which abstracts dynamics and makes the exploration process more robust.

Keywords: intrinsic motivation; deep reinforcement learning; information theory; developmental learning