A Spiking Neural Network Model of an Actor-Critic Learning Agent.
Wiebke PotjansAbigail MorrisonMarkus DiesmannPublished in: Neural Comput. (2009)
Keyphrases
- neural network model
- learning agent
- reinforcement learning
- reinforcement learning algorithms
- state space
- temporal difference
- neural network
- feed forward
- artificial neural networks
- function approximation
- solving problems
- learning algorithm
- learning capabilities
- model free
- markov decision processes
- learning tasks
- average reward
- policy iteration
- stochastic games
- learning rules
- rbf neural network
- reward function
- learning process
- multi agent systems
- machine learning
- fuzzy neural network
- fuzzy rules
- optimal policy
- single agent
- supervised learning