Realization of Reinforcement Learning using Multi-Winners KFM Associative Memory.
Takahiro IkeyaYuko OsanaPublished in: SMC (2009)
Keyphrases
- associative memory
- reinforcement learning
- storage capacity
- bi directional
- kohonen feature map
- state space
- neural network
- function approximation
- alpha beta
- neural network model
- auto associative
- learning algorithm
- multi agent
- learning process
- optimal policy
- machine learning
- support vector
- dynamic programming
- mobile robot
- data sets
- markov decision processes
- similarity measure