NEAT for large-scale reinforcement learning through evolutionary feature learning and policy gradient search.
Yiming PengGang ChenHarman SinghMengjie ZhangPublished in: GECCO (2018)
Keyphrases
- reinforcement learning
- policy gradient
- actor critic
- learning algorithm
- learning process
- function approximation
- temporal difference
- search algorithm
- reinforcement learning algorithms
- model free reinforcement learning
- function approximators
- learning problems
- supervised learning
- genetic algorithm
- optimal control
- learning capabilities
- reinforcement learning methods
- policy search
- policy gradient methods
- learning tasks
- action selection
- optimal policy
- search space
- multi agent
- machine learning