Reinforcement Learning by Probability Matching.
Philip N. SabesMichael I. JordanPublished in: NIPS (1995)
Keyphrases
- reinforcement learning
- matching process
- matching algorithm
- pattern matching
- probability distribution
- function approximation
- data sets
- computer vision
- multi agent
- state space
- feature points
- reinforcement learning algorithms
- confidence level
- real time
- matching scheme
- action selection
- image matching
- keypoints
- optimal policy
- dynamic programming
- neural network