Ronald Ortner INRIA Lille - Nord Europe, équipe SequeL Parc Scientifique de la Haute-Borne 40 avenue Halley 59650 Villeneuve d'Ascq, FRANCE E-mail   ronald.ortner@unileoben.ac.at

Life

Research Interests

Papers

Talks

Teaching/Lehre

The Informal Part

 

Life

	1973	born in Lienz

	Education

	1987 - 1991	attended the Bundesoberstufenrealgymnasium Lienz
	1991 - 2002	studies of mathematics, philosophy and computer science (among others) at the University of Salzburg
	Dec 1997	graduated with distinction in mathematics Diplomarbeit (Master thesis equivalent): "On Minimal Squared Rectangles"
	Dec 1998	graduated with distinction in philosophy Diplomarbeit (Master thesis equivalent): "On Solovay's Theorems of Arithmetical Completeness of the Modal Logic Systems GL and GLS"
	Jan 2002	received the doctorate in mathematics with distinction Doctoral Dissertation: "Arrangements of Pseudocircles" Supervisors: Prof. Dr. Johann Linhart, Prof. Dr. Peter Gerl.

	Awards

	Dec 1995	awarded the "Förderungspreis für hervorragende Studienleistungen" by the Department of Mathematics of the University of Salzburg
	Jun 2002	awarded the "Hans Stegbuchner-Preis" of the Department of Mathematics of the University of Salzburg for the Dissertation

	Profession

	Nov 1996 - May 1999	research fellow at the Institute of Philosophy of Science of the International Research Center Salzburg
	Jun 1999 - May 2000	alternative service at the Red Cross
	Jun 2000 - Sep 2002	employed at Infineon Technologies in Villach (area of responsibility: production logistics, line simulation)
	Oct 2002 - Jul 2003	assistant at the Department of Mathematics C of the TU Graz, research position in FWF-project P15577 "Asymptotic Properties of Random Walks on Graphs".
	Aug 2003 - Jun 2010	assistant professor at the Department Mathematik und Informationstechnologie of the Montanuniversität Leoben
	since July 2010	associate professor at the Department Mathematik und Informationstechnologie of the Montanuniversität Leoben (currently on leave)
	Jan 2012 - Oct 2012	Erwin Schrödinger scholarship (FWF J3259-N13) at INRIA Lille-Nord Europe (SequeL group)

	My Mathematical Genealogy

	My Erdös number

is 3 thanks to Wolfgang Woess (-> Carsten Thomassen -> Paul Erdös) and Peter Auer (-> Pal Revesz -> Paul Erdös).

	Research Interests (in reversed order of appearance)
	Markov Decision Processes and Reinforcement Learning Computational Learning Theory Random Walks Combinatorial Geometry (esp. Arrangements) Proof Theory (esp. Provability Logic) Graph Theory

	Papers
	Combinatorial Geometry:
	J.Linhart, R.Ortner: On the Combinatorial Structure of Arrangements of Oriented Pseudocircles Electron. J. Combin. 11 (2004), Research Paper 30, 13 pp. (electronic). (pdf) J.Linhart, R.Ortner: An Arrangement of Pseudocircles not Realizable with Circles, Beiträge Algebra Geom. Vol. 46, No. 2, pp. 351-356 (2005). (preprint pdf) R.Ortner: Embeddability of Arrangements of Pseudocircles into the Sphere, European J. Combin. 29, pp. 457-469 (2008). (corrected preprint pdf) R.Ortner: Improved Upper Bounds on the Number of Vertices of Weight <= k in Particular Arrangements of Pseudocircles, 24th European Workshop on Computational Geometry, pp. 35-38 (2008). (corrected version pdf) J.Linhart, R.Ortner: A Note on Convex Realizability of Arrangements of Pseudocircles, Geombinatorics Vol XVIII, Issue 2, pp. 66-71 (2008). (corrected version pdf)
	Random Walks:
	R.Ortner, W.Woess: Non-backtracking Random walks and Cogrowth of Graphs, Canadian J. Math. 59 / 4, pp. 828-844 (2007). (preprint pdf)
	Markov Decision Processes and Reinforcement Learning:
	P.Auer, R.Ortner: Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning, In: Advances in Neural Information Processing Systems 19 (2007), pp. 49-56. (pdf) R.Ortner: Linear Dependence of Stationary Distributions in Ergodic Markov Decision Processes , OR Letters 35 / 5, pp. 619-626 (2007). (preprint pdf) P.Auer, R.Ortner, and C. Szepesvári: Improved Rates for the Stochastic Continuum-Armed Bandit Problem, In: Learning Theory, 20th Annual Conference on Learning Theory, COLT 2007. Lecture Notes in Computer Science 4539, Springer 2007, pp. 454-468. (preprint pdf) R.Ortner: Pseudometrics for State Aggregation in Average Reward Markov Decision Processes, In: Proceedings of the 18th International Conference on Algorithmic Learning Theory, ALT 2007. Lecture Notes in Computer Science 4754, Springer 2007, pp. 373-387. (extended version pdf) R.Ortner: Online Regret Bounds for Markov Decision Processes with Deterministic Transitions, In: Proceedings of the 19th International Conference on Algorithmic Learning Theory, ALT 2008. Lecture Notes in Computer Science 5254, Springer 2008, pp. 123-137. (preprint pdf), (improved journal version pdf) R.Ortner: Optimism in the Face of Uncertainty Should be Refutable, Minds and Machines 18 / 4, pp. 521 - 526 (2008). (preprint pdf) P.Auer, T.Jaksch, and R.Ortner: Near-optimal Regret Bounds for Reinforcement Learning, In: Advances in neural information processing systems 21 (2009), pp. 89-96. R.Ortner: Online Regret Bounds for Markov Decision Processes with Deterministic Transitions, Theoretical Computer Science 411 / 29-30, pp. 2684-2695 (2010). (pdf) R.Ortner: Exploiting Similarity Information in Reinforcement Learning. Similarity Models for Multi-Armed Bandits and MDPs. In: ICAART 2010. Proceedings of the 2nd International Conference on Agents and Artificial Intelligence, Volume 1 (Artificial Intelligence), pp. 203-210. (pdf) T.Jaksch, R.Ortner, and P.Auer: Near-optimal Regret Bounds for Reinforcement Learning, J.Mach.Learn.Res. 11, pp. 1563-1600 (2010). P.Auer and R.Ortner: UCB Revisited: Improved Regret Bounds for the Stochastic Multi-Armed Bandit Problem, Period.Math.Hungar. 61 / 1-2, pp. 55-65 (2010). (corrected preprint pdf) R.Ortner: Adaptive Aggregation for Reinforcement Learning in Average Reward Markov Decision Processes, to appear in: Ann.Oper.Res. (preprint pdf)
	None of the above:
	P.Auer, R.Ortner: A New PAC-bound for Intersection-closed Concept Classes, In: Learning Theory, 17th Annual Conference on Learning Theory, COLT 2004. Lecture Notes in Computer Science 3120, Springer 2004, pp. 408-414. (extended version pdf) P.Auer, R.Ortner: A Boosting Approach to Multiple Instance Learning, In: Machine Learning, 15th European Conference on Machine Learning, ECML 2004. Lecture Notes in Artificial Intelligence 3201, Springer 2004, pp. 63-74. (extended version pdf) P.Auer, R.Ortner: A New PAC-bound for Intersection-closed Concept Classes, In: Machine Learning, Vol. 66, No. 2-3, pp. 151-163 (2007). (preprint pdf) M.Antenreiter, R. Ortner, and Peter Auer: Combining Classifiers for Improved Multilabel Image Classification, In: Learning from Multi-label Data, MLD Workshop at ECML 2009, pp. 16-27. (pdf) H.Leitgeb and R.Ortner: Mechanizing Induction, To appear in: Dov Gabbay, Stephan Hartmann, John Woods (ed.), Handbook for the History of Logic, Vol. 10: Inductive Logic. Elsevier.

	Talks (that are not associated with any of the papers above)
	To generalise is to be an idiot - or a machine. Machine learning and the problem of induction, ESF Exploratory Workshop on Applied Logic in the Methodology of Science, Bristol 8-10 September 2006. (slides pdf)

	Teaching/Lehre
	meine Lehrveranstaltungen im MU Online die Lehrveranstaltung "IT I" auf der Institutshomepage

to the top

back to the department

to the (hopelessly outdated) informal part

---

Last modified on January 5, 2011