Correlation minimizing replay memory in temporal-difference reinforcement learning.
Mirza RamicicAndrea BonariniPublished in: Neurocomputing (2020)
Keyphrases
- temporal difference
- reinforcement learning
- function approximation
- td learning
- past experience
- model free
- temporal difference learning
- evaluation function
- reinforcement learning algorithms
- function approximators
- action selection
- state space
- policy evaluation
- monte carlo
- step size
- policy iteration
- temporal difference methods
- supervised learning
- actor critic
- objective function
- learning algorithm
- multi agent
- genetic algorithm
- td methods
- machine learning