Markov Decision Process for Video Generation.
Vladyslav YushchenkoNikita AraslanovStefan RothPublished in: CoRR (2019)
Keyphrases
- markov decision process
- markov decision processes
- state space
- optimal policy
- reinforcement learning
- video sequences
- temporal difference learning
- video data
- finite horizon
- policy iteration
- infinite horizon
- transition matrices
- real time
- average cost
- transition probabilities
- initial state
- dynamic systems
- multistage
- linear programming
- machine learning