Actor-Critic Models of Reinforcement Learning in the Basal Ganglia: From Natural to Artificial Rats.
Mehdi KhamassiLoïc LachèzeBenoît GirardAlain BerthozAgnès GuillotPublished in: Adapt. Behav. (2005)
Keyphrases
- reinforcement learning
- basal ganglia
- actor critic
- action selection
- temporal difference
- function approximation
- optimal control
- neural network
- connectionist models
- reinforcement learning algorithms
- approximate dynamic programming
- learning algorithm
- fuzzy logic
- transfer learning
- human brain
- average reward
- policy gradient
- state space