An Approach to the Piano Mover's Problem Using Hierarchic Reinforcement Learning.
Yuko IshiwakaTomohiro YoshidaHiroshi YokoiYukinori KakazuPublished in: IEICE Trans. Inf. Syst. (2004)
Keyphrases
- reinforcement learning
- learning algorithm
- state space
- reinforcement learning algorithms
- function approximation
- multi agent reinforcement learning
- optimal policy
- reinforcement learning methods
- machine learning
- model free
- optimal control
- continuous state
- control problems
- markov decision processes
- partially observable
- learning agents
- transfer learning
- multi agent
- transition model