Temporal Difference Variational Auto-Encoder.
Karol GregorGeorge PapamakariosFrederic BesseLars BuesingTheophane WeberPublished in: ICLR (2019)
Keyphrases
- temporal difference
- reinforcement learning
- td learning
- evaluation function
- function approximation
- monte carlo
- step size
- temporal difference learning
- bit rate
- model free
- reinforcement learning algorithms
- image segmentation
- action selection
- optical flow
- temporal difference methods
- policy iteration
- supervised learning
- function approximators
- policy evaluation
- neural network
- optimal policy
- markov chain
- cost function