Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks.
Sina GhiassianBanafsheh RafieeYat Long LoAdam WhitePublished in: CoRR (2020)
Keyphrases
- neural network
- reinforcement learning
- function approximators
- function approximation
- artificial neural networks
- learning capabilities
- reinforcement learning algorithms
- pattern recognition
- genetic algorithm
- optimal control
- fault diagnosis
- learning classifier systems
- fuzzy systems
- multilayer perceptron
- markov decision processes
- fuzzy logic
- data mining
- machine learning
- least squares
- learning algorithm
- temporal difference
- dynamic programming
- transition model
- back propagation
- markov decision process
- action selection
- multi agent
- training algorithm
- multi layer
- state space
- recurrent neural networks
- supervised learning
- self organizing maps
- data sets
- optimal policy