Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Model-free reinforcement learning from expert demonstrations: a survey

Model-free reinforcement learning from expert demonstrations: a survey Reinforcement learning from expert demonstrations (RLED) is the intersection of imitation learning with reinforcement learning that seeks to take advantage of these two learning approaches. RLED uses demonstration trajectories to improve sample efficiency in high-dimensional spaces. RLED is a new promising approach to behavioral learning through demonstrations from an expert teacher. RLED considers two possible knowledge sources to guide the reinforcement learning process: prior knowledge and online knowledge. This survey focuses on novel methods for model-free reinforcement learning guided through demonstrations, commonly but not necessarily provided by humans. The methods are analyzed and classified according to the impact of the demonstrations. Challenges, applications, and promising approaches to improve the discussed methods are also discussed. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Artificial Intelligence Review Springer Journals

Model-free reinforcement learning from expert demonstrations: a survey

Loading next page...
 
/lp/springer-journals/model-free-reinforcement-learning-from-expert-demonstrations-a-survey-G9EF9FEocK
Publisher
Springer Journals
Copyright
Copyright © The Author(s), under exclusive licence to Springer Nature B.V. 2021
ISSN
0269-2821
eISSN
1573-7462
DOI
10.1007/s10462-021-10085-1
Publisher site
See Article on Publisher Site

Abstract

Reinforcement learning from expert demonstrations (RLED) is the intersection of imitation learning with reinforcement learning that seeks to take advantage of these two learning approaches. RLED uses demonstration trajectories to improve sample efficiency in high-dimensional spaces. RLED is a new promising approach to behavioral learning through demonstrations from an expert teacher. RLED considers two possible knowledge sources to guide the reinforcement learning process: prior knowledge and online knowledge. This survey focuses on novel methods for model-free reinforcement learning guided through demonstrations, commonly but not necessarily provided by humans. The methods are analyzed and classified according to the impact of the demonstrations. Challenges, applications, and promising approaches to improve the discussed methods are also discussed.

Journal

Artificial Intelligence ReviewSpringer Journals

Published: Oct 18, 2021

Keywords: Reinforcement learning; Imitation learning; Learning from demonstrations; Behavioral learning; Demonstrations

References