Asymptotics of Reinforcement Learning with Neural Networks.
Justin A. SirignanoKonstantinos SpiliopoulosPublished in: CoRR (2019)
Keyphrases
- neural network
- reinforcement learning
- function approximation
- function approximators
- pattern recognition
- state space
- optimal policy
- learning classifier systems
- artificial neural networks
- learning process
- markov chain
- learning algorithm
- learning capabilities
- model free
- fuzzy systems
- markov decision processes
- multi agent
- back propagation
- fuzzy logic
- multi layer
- sufficient conditions
- reinforcement learning algorithms
- dynamic programming
- robotic control
- stochastic approximation
- large deviations
- robot control
- hidden markov models
- temporal difference
- self organizing maps
- multilayer perceptron
- feed forward
- neural network model
- fault diagnosis