Meta-Gradient Reinforcement Learning.
Zhongwen XuHado van HasseltDavid SilverPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- policy gradient
- function approximation
- optimal policy
- model free
- reinforcement learning algorithms
- learning algorithm
- gradient information
- state space
- machine learning
- gradient method
- temporal difference
- optimal control
- markov decision processes
- edge detection
- learning process
- multi agent
- dynamic programming
- gradient direction
- policy search
- learning classifier systems
- action selection
- domain knowledge
- image gradient
- multi agent systems
- gradient field
- data sets
- robotic control
- search results clustering