Online Markov Decision Processes With Kullback-Leibler Control Cost.
Peng GuanMaxim RaginskyRebecca M. WillettPublished in: IEEE Trans. Autom. Control. (2014)
Keyphrases
- markov decision processes
- kullback leibler
- average cost
- finite state
- optimal policy
- state space
- transition matrices
- reinforcement learning
- dynamic programming
- kl divergence
- cross entropy
- decision theoretic planning
- distance measure
- policy iteration
- kullback leibler divergence
- infinite horizon
- optimal control
- average reward
- long run
- markov decision process
- machine learning
- information theory
- real time dynamic programming
- information theoretic
- mutual information
- collaborative filtering
- semi supervised
- cost function
- image segmentation