Adaptive action selection using utility-based reinforcement learning.
Kunrong ChenFen LinQing TanZhongzhi ShiPublished in: GrC (2009)
Keyphrases
- action selection
- reinforcement learning
- temporal difference
- basal ganglia
- robot soccer
- decision making
- action space
- human robot
- continuous state and action spaces
- machine learning
- optimal policy
- state space
- adaptive control
- action selection mechanism
- optimal control
- dynamic programming
- neural network
- model free
- partially observable
- temporal difference learning
- total reward