Operational "Feel" Adjustment by Reinforcement Learning for a Power-Assisted Positioning Task.
Tetsuya MorizonoYoji YamadaMasatake HigashiPublished in: Int. J. Autom. Technol. (2009)
Keyphrases
- reinforcement learning
- function approximation
- optimal policy
- neural network
- machine learning
- robotic control
- temporal difference learning
- reinforcement learning algorithms
- temporal difference
- power consumption
- state space
- dynamic programming
- learning process
- decision making
- sufficient conditions
- transfer learning
- markov decision processes
- model free
- decision trees
- learning algorithm
- power distribution
- real world