Efficient Exploration through Intrinsic Motivation Learning for Unsupervised Subgoal Discovery in Model-Free Hierarchical Reinforcement Learning
Machine Learning
2019-11-25 v1 Artificial Intelligence
Machine Learning
Abstract
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 exploration, leading to successful subgoal discovery. We introduce a model-free subgoal discovery method based on unsupervised learning over a limited memory of agent's experiences during intrinsic motivation. Additionally, we offer a unified approach to learning representations in model-free HRL.
Keywords
Cite
@article{arxiv.1911.10164,
title = {Efficient Exploration through Intrinsic Motivation Learning for Unsupervised Subgoal Discovery in Model-Free Hierarchical Reinforcement Learning},
author = {Jacob Rafati and David C. Noelle},
journal= {arXiv preprint arXiv:1911.10164},
year = {2019}
}
Comments
arXiv admin note: substantial text overlap with arXiv:1810.10096