An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey
This is an incremental survey that addresses exploration challenges in reinforcement learning for researchers in the field.
The paper surveys intrinsic motivation in reinforcement learning through an information-theoretic taxonomy, revisiting concepts like surprise and novelty to analyze methods and identify research outlooks, suggesting that these concepts can help build transferable skill hierarchies for more robust exploration.
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.