Ronald Ortner

Research output

  1. 2008
  2. Published

    Near-optimal Regret Bounds for Reinforcement Learning

    Auer, P., Jaksch, T. & Ortner, R., 2008.

    Research output: Contribution to conferencePosterResearchpeer-review

  3. Published

    Online Regret Bounds for Markov Decision Processes with Deterministic Transitions

    Ortner, R., 2008, Proceedings of the 19th International Conference on Algorithmic Learning Theory. p. 123-137

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  4. Published

    Optimism in the Face of Uncertainty Should be Refutable

    Ortner, R., 2008, In: Minds and Machines. 18, p. 521-526

    Research output: Contribution to journalArticleResearchpeer-review

  5. 2007
  6. Published

    A new PAC bound for intersection-closed concept classes

    Auer, P. & Ortner, R., 2007, In: Machine learning. 66, p. 151-163

    Research output: Contribution to journalArticleResearchpeer-review

  7. Published

    Improved Rates for the Stochastic Continuum-Armed Bandit Problem

    Auer, P., Ortner, R. & Szepesvári, C., 2007, Proceedings of the 20th Annual Conference on Learning Theory. Springer, p. 454-468

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  8. Published

    Linear dependence of stationary distributions in ergodic Markov decision processes

    Ortner, R., 2007, In: Operations Research Letters. 35, p. 619-626

    Research output: Contribution to journalArticleResearchpeer-review

  9. Published

    Logarithmic online regret bounds for undiscounted reinforcement learning

    Auer, P. & Ortner, R., 2007, Advances in Neural Information Processing Systems 19. MIT Press, p. 49-56

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  10. Published

    Non-backtracking random walks and cogrowth of graphs

    Ortner, R. & Woess, W., 2007, In: Canadian journal of mathematics : Journal canadien de mathématiques. 59, p. 828-844

    Research output: Contribution to journalArticleResearchpeer-review

  11. Published

    Pseudometrics for State Aggregation in Average Reward Markov Decision Processes

    Ortner, R., 2007, Proceedings of the 18th International Conference on Algorithmic Learning Theory. p. 373-387

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  12. 2006
  13. Published

    Empirical evaluation of a new online reinforcement learning algorithm

    Auer, P., Jaksch, T. & Ortner, R., 2006

    Research output: Book/ReportCommissioned reportTransferpeer-review

  14. Published

    Logarithmic online regret bounds for undiscounted reinforcement learning

    Auer, P. & Ortner, R., 2006.

    Research output: Contribution to conferencePosterResearchpeer-review

  15. Published

    Pawlow'sche Steuerungen

    Ortner, R., 2006.

    Research output: Contribution to conferencePosterResearchpeer-review

  16. 2005
  17. Published

    A boosting approach to multiple-instance learning

    Auer, P. & Ortner, R., 2005

    Research output: Book/ReportCommissioned reportTransferpeer-review

  18. Published

    An Arrangement of Pseudocircles not Realizable with Circles

    Linhart, J. & Ortner, R., 2005, In: Beiträge zur Algebra und Geometrie = Contributions to algebra and geometry. 46, p. 351-356

    Research output: Contribution to journalArticleResearchpeer-review

  19. Published

    Combinations and Mixtures of Optimal Policies in Unichain MDPs are Optimal: arXiv.org e-Print archive

    Ortner, R., 2005

    Research output: Non-textual formWeb publication/siteResearch

  20. Published

    Online Regret Bounds for a New Reinforcement Learning Algorithm

    Auer, P. & Ortner, R., 2005, 1st Austrian Cognitive Vision Workshop. Österr. Computer-Ges., p. 35-42

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  21. 2004
  22. Published

    A Boosting Approach to Multiple Instance Learning

    Auer, P. & Ortner, R., 2004, Machine Learning, 15th European Conference on Machine Learning, ECML 2004. Springer, p. 63-74

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  23. Published

    A New PAC-bound for Intersection-closed Concept Classes

    Auer, P. & Ortner, R., 2004, Learning Theory, 17th Annual Conference on Learning Theory. Springer, p. 408-414

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  24. Published

    On the Combinatorial Structure of Arrangements of Oriented Pseudocircles

    Linhart, J. & Ortner, R., 2004, In: The journal of combinatorics. 11, p. R30-R30

    Research output: Contribution to journalArticleResearchpeer-review

Previous 1 2 3 4 Next