Effective Policy Gradient Search for Reinforcement Learning Through NEAT Based Feature Extraction.
Yiming PengGang ChenMengjie ZhangYi MeiPublished in: SEAL (2017)
Keyphrases
- policy gradient
- reinforcement learning
- feature extraction
- function approximation
- search algorithm
- reinforcement learning algorithms
- actor critic
- search space
- state space
- temporal difference
- policy gradient methods
- markov chain
- policy search
- optimal control
- markov decision processes
- neural network
- supervised learning
- multi agent
- face recognition