Using epsiloon-greedy reinforcement learning methods to further understand ventromedial prefrontal patients' deficits on the Iowa Gambling Task.
Kiran KalidindiHoward BowmanPublished in: Neural Networks (2007)
Keyphrases
- reinforcement learning methods
- reinforcement learning
- dynamical systems
- reinforcement learning algorithms
- search algorithm
- control problems
- model construction
- model free
- search space
- dynamic programming
- neural network
- control strategies
- control strategy
- action space
- hill climbing
- optimal control
- mobile robot
- control system
- multi agent
- genetic algorithm