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

2022-09-19 · Arthur Aubret, Laetitia Matignon, Salima Hassas

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.

📄 PDF Abstract BibTeX arXiv:2209.08890

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning (RL)

A survey on intrinsic motivation in reinforcement learning

2019-08-19 · Arthur Aubret, Laetitia Matignon, Salima Hassas

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Survey

Intrinsic Motivation in Dynamical Control Systems

2022-12-29 · Stas Tiomkin, Ilya Nemenman, Daniel Polani, Naftali Tishby

Biological systems often choose actions without an explicit reward signal, a phenomenon known as intrinsic motivation. The computational principles underlying this behavior remain poorly understood. In this study, we inv…

Intrinsic motivations and open-ended learning

2019-12-31 · Gianluca Baldassarre

There is a growing interest and literature on intrinsic motivations and open-ended learning in both cognitive robotics and machine learning on one side, and in psychology and neuroscience on the other. This paper aims to…

BIG-bench Machine Learning

Efficient Exploration through Intrinsic Motivation Learning for Unsupervised Subgoal Discovery in Model-Free Hierarchical Reinforcement Learning

2019-11-18 · Jacob Rafati, David C. Noelle

Efficient exploration for automatic subgoal discovery is a challenging problem in Hierarchical Reinforcement Learning (HRL). In this paper, we show that intrinsic motivation learning increases the efficiency of explorati…

Efficient Exploration Hierarchical Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Intrinsic motivation as constrained entropy maximization

2025-02-05 · Alex B. Kiefer

"Intrinsic motivation" refers to the capacity for intelligent systems to be motivated endogenously, i.e. by features of agential architecture itself rather than by learned associations between action and reward. This pap…