An Experimental Comparison Between Temporal Difference and Residual Gradient with Neural Network Approximation.
Shuyu YinTao LuoPeilin LiuZhi-Qin John XuPublished in: CoRR (2022)
Keyphrases
- temporal difference
- neural network
- td learning
- function approximators
- function approximation
- reinforcement learning
- policy evaluation
- evaluation function
- approximation methods
- monte carlo
- temporal difference learning
- model free
- step size
- reinforcement learning algorithms
- action selection
- artificial neural networks
- pattern recognition
- radial basis function
- genetic algorithm
- supervised learning
- policy iteration
- gradient method
- actor critic
- reinforcement learning problems