Obserwuj
Romain Hollanders
Romain Hollanders
Ph.D. Student, Université catholique de Louvain, ICTEAM, EPL
Zweryfikowany adres z uclouvain.be
Tytuł
Cytowane przez
Cytowane przez
Rok
The complexity of policy iteration is exponential for discounted Markov decision processes
R Hollanders, JC Delvenne, RM Jungers
2012 IEEE 51st IEEE Conference on Decision and Control (CDC), 5997-6002, 2012
352012
Improved bound on the worst case complexity of Policy Iteration
R Hollanders, B Gerencsér, JC Delvenne, RM Jungers
Operations Research Letters 44 (2), 267-272, 2016
152016
A complexity analysis of Policy Iteration through combinatorial matrices arising from Unique Sink Orientations
B Gerencsér, R Hollanders, JC Delvenne, RM Jungers
Journal of Discrete Algorithms 44, 21-38, 2017
82017
Data-driven traffic and diffusion modeling in peer-to-peer networks: A real case study
R Hollanders, DF Bernardes, B Mitra, RM Jungers, JC Delvenne, ...
Network Science 2 (3), 341-366, 2014
32014
On the policy iteration algorithm for PageRank optimization
R Hollanders, R Jungers
Master’s thesis, Université Catholique de Louvain, June 2010. Available from …, 2010
32010
About upper bounds on the complexity of Policy Iteration
R Hollanders, B Gerencsér, JC Delvenne, RM Jungers
Submitted, 2014
12014
Tight bounds on sparse perturbations of Markov chains
R Hollanders, G Como, JC Delvenne, RM Jungers
International Symposium on Mathematical Theory of Networks and Systems, 2014
12014
Policy Iteration is well suited to optimize PageRank
R Hollanders, JC Delvenne, R Jungers
arXiv preprint arXiv:1108.3779, 2011
12011
Decision making in large stochastic and adversarial environments
R Hollanders
Université de Lorraine, France, 2015
2015
A complexity analysis of Policy Iteration
B Gerencsér, R Hollanders, JC Delvenne, RM Jungers
arXiv preprint arXiv:1407.4293, 2014
2014
An improved lower bound for Order-Regular matrices.
R Hollanders, B Gerencsér, JC Delvenne, RM Jungers
arXiv preprint arXiv:1407.4293, 2014
2014
Special issue in the honor of the 14th “Journées Montoises d’Informatique Théorique”: Foreword
R Jungers, V Bruyère, R Hollanders, M Rigo
RAIRO-Theoretical Informatics and Applications 48 (3), 247-247, 2014
2014
Foreword to the Special Issue in the honor of the Journées Montoises 2014
RM Jungers, V Bruyère, R Hollanders, M Rigo
RAIRO-Theoretical Informatics and Applications 48, 247, 2014
2014
Special Issue of RAIRO TIA in the honor of the 14th Mons Days of Theoretical Computer Science
RM Jungers, V Bruyère, R Hollanders, M Rigo
RAIRO-Theoretical Informatics and Applications, 2014
2014
A new upper bound for Policy Iteration
R Hollanders, B Gerencsér, JC Delvenne, RM Jungers
21st International Symposium on Mathematical Theory of Networks and Systems, 2014
2014
A combinatorial open problem for the complexity of policy iteration
R Hollanders, JC Delvenne, RM Jungers
32nd Benelux Meeting on Systems and Control, 2013
2013
An exponential lower-bound for the Policy iteration algorithm on discounted MDPs
R Hollanders, JC Delvenne, RM Jungers
CDC 2012, 2012
2012
On the complexity of optimizing PageRank
R Hollanders, JC Delvenne, RM Jungers
14èmes Rencontres Francophones sur les Aspects Algorithmiques des …, 2012
2012
About the latest complexity bounds for Policy Iteration1
R Hollanders, B Gerencsér, JC Delvenne, RM Jungers
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–19