An Information-Theoretic Perspective on Intrinsic Motivation in Reinforcement Learning: A Survey - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Entropy Année : 2023

An Information-Theoretic Perspective on Intrinsic Motivation in Reinforcement Learning: A Survey

Résumé

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.

Dates et versions

hal-04093961 , version 1 (10-05-2023)

Identifiants

Citer

Arthur Aubret, Laëtitia Matignon, Salima Hassas. An Information-Theoretic Perspective on Intrinsic Motivation in Reinforcement Learning: A Survey. Entropy, 2023, 25 (2), pp.327. ⟨10.3390/e25020327⟩. ⟨hal-04093961⟩
17 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More