Model-Free Local Recalibration of Neural Networks.
R. TorresDavid J. NottScott A. SissonT. RodriguesJ. G. ReisG. S. RodriguesPublished in: CoRR (2024)
Keyphrases
- model free
- neural network
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- pattern recognition
- temporal difference
- policy iteration
- back propagation
- genetic algorithm
- policy evaluation
- artificial neural networks
- average reward
- machine learning
- learning tasks
- supervised learning
- learning algorithm