Model-free learning on robot kinematic chains using a nested multi-agent topology.
John N. KarigiannisCostas S. TzafestasPublished in: J. Exp. Theor. Artif. Intell. (2016)
Keyphrases
- reinforcement learning
- model free
- multi agent
- learning process
- learning algorithm
- active learning
- autonomous robots
- mobile robot
- supervised learning
- function approximation
- robot control
- machine learning
- reinforcement learning algorithms
- temporal difference
- labeled data
- semi supervised
- dynamic programming
- learning environment