Intensive versus Non-intensive Actor-Critic Reinforcement Learning Algorithms.
Pawel WawrzynskiAndrzej PacutPublished in: ICAISC (2004)
Keyphrases
- reinforcement learning algorithms
- actor critic
- reinforcement learning
- policy gradient
- temporal difference
- model free
- state space
- markov decision processes
- function approximation
- reinforcement learning methods
- reinforcement learning problems
- neuro fuzzy
- machine learning
- optimal control
- gradient method
- evaluation function
- stochastic games
- temporal difference learning
- supervised learning
- least squares
- optimal solution