On the Performance of Temporal Difference Learning With Neural Networks.
Haoxing TianIoannis Ch. PaschalidisAlex OlshevskyPublished in: CoRR (2023)
Keyphrases
- temporal difference learning
- neural network
- function approximation
- function approximators
- fixed point
- reinforcement learning
- evaluation function
- game playing
- pattern recognition
- approximate value iteration
- reinforcement learning algorithms
- temporal difference
- artificial neural networks
- radial basis function
- monte carlo
- markov decision process
- genetic algorithm
- linear combination