Rationally inattentive Markov decision processes over a finite horizon.
Ehsan ShafieepoorfardMaxim RaginskyPublished in: ACSSC (2017)
Keyphrases
- finite horizon
- markov decision processes
- optimal policy
- optimal stopping
- infinite horizon
- average cost
- state space
- decision theoretic planning
- reinforcement learning
- finite state
- dynamic programming
- policy iteration
- transition matrices
- markov decision process
- partially observable
- control policies
- action space
- data mining
- machine learning