Chaos-Based Reinforcement Learning When Introducing Refractoriness in Each Neuron.
Katsuki SatoYuki GotoKatsunari ShibataPublished in: RiTA (2018)
Keyphrases
- reinforcement learning
- function approximation
- neural network
- learning algorithm
- learning problems
- state space
- model free
- multi agent
- optimal policy
- machine learning
- learning process
- markov decision processes
- data sets
- optimal control
- action selection
- temporal difference
- action space
- stochastic approximation
- multi agent reinforcement learning
- neuron model