Next Article in Journal
A Compact UWB Bandpass Chip Filter on a GaAs Substrate with Modified Chebyshev Structure
Previous Article in Journal
Sea Fog Identification From GOCI Images Using CNN Transfer Learning Models
Open AccessArticle

Intrinsic Motivation Based Hierarchical Exploration for Model and Skill Learning

College of Intelligence Science and Technology, National University of Defense Technology, Changsha, Hunan, 410073, China
*
Author to whom correspondence should be addressed.
Electronics 2020, 9(2), 312; https://doi.org/10.3390/electronics9020312
Received: 6 January 2020 / Revised: 26 January 2020 / Accepted: 8 February 2020 / Published: 11 February 2020
(This article belongs to the Special Issue Cognitive Robotics)
Hierarchical skill learning is an important research direction in human intelligence. However, many real-world problems have sparse rewards and a long time horizon, which typically pose challenges in hierarchical skill learning and lead to the poor performance of naive exploration. In this work, we propose an algorithmic framework called surprise-based hierarchical exploration for model and skill learning (Surprise-HEL). The framework leverages the surprise-based intrinsic motivation for improving the efficiency of sampling and driving exploration. It also combines the surprise-based intrinsic motivation and the hierarchical exploration to speed up the model learning and skill learning. Moreover, the framework incorporates the reward independent incremental learning rules and the technique of alternating model learning and policy update to handle the changing intrinsic rewards and the changing models. These works enable the framework to implement the incremental and developmental learning of models and hierarchical skills. We tested Surprise-HEL on a common benchmark domain: Household Robot Pickup and Place. The evaluation results show that the Surprise-HEL framework can significantly improve the agent’s efficiency in model and skill learning in a typical complex domain.
Keywords: intrinsic motivation; robot intelligence; model learning; skill learning; reinforcement learning intrinsic motivation; robot intelligence; model learning; skill learning; reinforcement learning
MDPI and ACS Style

Lu, L.; Zhang, W.; Gu, X.; Chen, J. Intrinsic Motivation Based Hierarchical Exploration for Model and Skill Learning. Electronics 2020, 9, 312.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop