An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey

TL;DR

This survey reviews how information-theoretic concepts like surprise and novelty are used to enhance intrinsic motivation in reinforcement learning, aiding exploration and skill transfer especially in sparse-reward environments.

Contribution

It introduces a new taxonomy based on information theory to analyze intrinsic motivation methods in RL, highlighting their advantages and limitations.

Findings

Novelty and surprise help build transferable skill hierarchies.

Intrinsic motivation improves exploration in sparse-reward settings.

Information-theoretic analysis clarifies method strengths and weaknesses.

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, amongst which we can mention 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 that further abstracts the environment and makes the exploration process more robust.