Search the dblp DataBase

Publications of Author

1. Peter Auer, Ronald Ortner
   A New PAC Bound for Intersection-Closed Concept Classes. [Citation Graph (0, 0)][DBLP]
   COLT, 2004, pp:408-414 [Conf]
   
2. Peter Auer, Ronald Ortner
   A Boosting Approach to Multiple Instance Learning. [Citation Graph (0, 0)][DBLP]
   ECML, 2004, pp:63-74 [Conf]
   
3. Johann Linhart, Ronald Ortner
   On the Combinatorial Structure of Arrangements of Oriented Pseudocircles. [Citation Graph (0, 0)][DBLP]
   Electr. J. Comb., 2004, v:11, n:1, pp:- [Journal]
   
4. Ronald Ortner
   Pseudometrics for State Aggregation in Average Reward Markov Decision Processes. [Citation Graph (0, 0)][DBLP]
   ALT, 2007, pp:373-387 [Conf]
   
5. Peter Auer, Ronald Ortner, Csaba Szepesvári
   Improved Rates for the Stochastic Continuum-Armed Bandit Problem. [Citation Graph (0, 0)][DBLP]
   COLT, 2007, pp:454-468 [Conf]
   
6. Peter Auer, Ronald Ortner
   Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning. [Citation Graph (0, 0)][DBLP]
   NIPS, 2006, pp:49-56 [Conf]
   
7. Peter Auer, Ronald Ortner
   A new PAC bound for intersection-closed concept classes. [Citation Graph (0, 0)][DBLP]
   Machine Learning, 2007, v:66, n:2-3, pp:151-163 [Journal]
   
8. 
   Online Regret Bounds for Markov Decision Processes with Deterministic Transitions. [Citation Graph (, )][DBLP]
   
   
9. 
   Near-optimal Regret Bounds for Reinforcement Learning. [Citation Graph (, )][DBLP]
   
   
10. 
    Exploiting Similarity Information in Reinforcement Learning - Similarity Models for Multi-Armed Bandits and MDPs. [Citation Graph (, )][DBLP]
    
    
11. 
    Combinations and Mixtures of Optimal Policies in Unichain Markov Decision Processes are Optimal [Citation Graph (, )][DBLP]
    
    
12. 
    Embeddability of Arrangements of Pseudocircles into the Sphere [Citation Graph (, )][DBLP]
    
    
13. 
    Embeddability of arrangements of pseudocircles into the sphere. [Citation Graph (, )][DBLP]