Title
Transfer-Entropy-Regularized Markov Decision Processes
Abstract
We consider the framework of transfer-entropy-regularized Markov decision process (TERMDP) in which the weighted sum of the classical state-dependent cost and the transfer entropy from the state random process to the control input process is minimized. Although TERMDPs are generally formulated as nonconvex optimization problems, an analytical necessary optimality condition can be expressed as a fi...
Year
DOI
Venue
2022
10.1109/TAC.2021.3069347
IEEE Transactions on Automatic Control
Keywords
DocType
Volume
Entropy,Random processes,Standards,Markov processes,Thermodynamics,Rate-distortion,Optimization
Journal
67
Issue
ISSN
Citations 
4
0018-9286
0
PageRank 
References 
Authors
0.34
0
3
Name
Order
Citations
PageRank
Takashi Tanaka13412.22
Henrik Sandberg21215112.50
Mikael Skoglund31397175.71