Research Area: Machine Learning
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.
Keywords:
Reinforcement learning
Imitation learning
Learning from demonstrations
Behavioral learning
Demonstrations
Author(s) Name: Jorge Ramírez, Wen Yu & Adolfo Perrusquía
Journal name: Artificial Intelligence Review
Conferrence name:
Publisher name: Springer
DOI: 10.1007/s10462-021-10085-1
Volume Information: volume 55, pages: 3213–3241
