A Complementary Learning Systems Approach to Temporal Difference Learning.
Sam BlakemanDenis MareschalPublished in: CoRR (2019)
Keyphrases
- learning systems
- temporal difference learning
- fixed point
- function approximation
- reinforcement learning
- evaluation function
- game playing
- temporal difference
- machine learning
- approximate value iteration
- learning styles
- learning environment
- reinforcement learning algorithms
- learning process
- markov decision process
- policy iteration
- monte carlo
- decision making
- gaussian process
- data mining
- action selection
- dynamic environments
- markov chain
- dynamic programming
- decision trees
- metadata
- technology enhanced learning systems