Forgetting in Reinforcement Learning Links Sustained Dopamine Signals to Motivation.
Ayaka KatoKenji MoritaPublished in: PLoS Comput. Biol. (2016)
Keyphrases
- reinforcement learning
- temporal difference
- function approximation
- incremental learning
- autonomous learning
- signal processing
- markov decision processes
- robotic control
- action selection
- link analysis
- learning process
- multi agent
- state space
- basal ganglia
- learning algorithm
- reinforcement learning algorithms
- transfer learning
- transition model
- signal detection
- knowledge building
- model free
- input signals
- radio frequency
- machine learning
- neural network
- semi markov
- markov decision process
- decision trees
- evaluation function
- independent component analysis
- optimal policy