Lateral Inhibition Overcomes Limits of Temporal Difference Learning.
Jacob RafatiDavid C. NoellePublished in: CogSci (2015)
Keyphrases
- temporal difference learning
- lateral inhibition
- function approximation
- fixed point
- evaluation function
- spreading activation
- game playing
- reinforcement learning
- temporal difference
- receptive fields
- monte carlo
- markov decision process
- reinforcement learning algorithms
- semantic network
- machine learning
- markov decision processes
- supervised learning
- image features
- feature extraction