Stability of Stochastic Approximations With "Controlled Markov" Noise and Temporal Difference Learning.
Arunselvan RamaswamyShalabh BhatnagarPublished in: IEEE Trans. Autom. Control. (2019)
Keyphrases
- temporal difference learning
- function approximation
- fixed point
- evaluation function
- monte carlo
- approximate value iteration
- reinforcement learning
- game playing
- temporal difference
- noise level
- markov chain
- closed form
- markov model
- learning tasks
- least squares
- reinforcement learning algorithms
- supervised learning
- markov decision process
- image segmentation