Sparse randomized policies for Markov decision processes based on Tsallis divergence regularization
-
Published:2024-09
Issue:
Volume:300
Page:112105
-
ISSN:0950-7051
-
Container-title:Knowledge-Based Systems
-
language:en
-
Short-container-title:Knowledge-Based Systems
Author:
Leleux Pierre,
Lebichot BertrandORCID,
Guex Guillaume,
Saerens Marco
Funder
Innoviris
Norges Forskningsråd
Reference97 articles.
1. Cyclic flows, Markov process and stochastic traffic assignment;Akamatsu;Transp. Res. B,1996
2. Alternatives to dial’s logit assignment algorithm;Bell;Transp. Res. B,1995
3. A probabilistic multipath assignment model that obviates path enumeration;Dial;Transp. Res.,1971
4. Randomized shortest-path problems: Two related models;Saerens;Neural Comput.,2009
5. L. Yen, A. Mantrach, M. Shimbo, M. Saerens, A family of dissimilarity measures between nodes generalizing both the shortest-path and the commute-time distances, in: Proceedings of the 14th SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2008, 2008, pp. 785–793.