Gradient Temporal-Difference Learning with Regularized Corrections.
Sina GhiassianAndrew PattersonShivam GargDhawal GuptaAdam WhiteMartha WhitePublished in: ICML (2020)
Keyphrases
- temporal difference learning
- function approximation
- fixed point
- evaluation function
- reinforcement learning
- game playing
- approximate value iteration
- temporal difference
- markov decision process
- reinforcement learning algorithms
- least squares
- monte carlo
- neural network
- linear combination
- support vector machine
- state space
- image segmentation
- learning algorithm