BibSonomy :: author  ::

bookmarks

publications

(9)

• Online convex optimization in the bandit setting: gradient descent without a gradient
  Abraham Flaxman and Adam Tauman Kalai and H. Brendan McMahan CoRR cs.LG/0408007 (2004)
  to dblp by dblp on 2008-01-02 00:00:00
  | URL | BibTeX  
• Efficiently computing minimax expected-size confidence regions.
  Brent Bryan and H. Brendan McMahan and Chad M. Schafer and Jeff G. Schneider ICML 97-104 (2007)
  to dblp by dblp on 2007-10-22 00:00:00
  | URL | BibTeX  
• A Unification of Extensive-Form Games and Markov Decision Processes.
  H. Brendan McMahan and Geoffrey J. Gordon AAAI 86-93 (2007)
  to dblp by dblp on 2007-09-05 00:00:00
  | URL | BibTeX  
• Bounded real-time dynamic programming: RTDP with monotone upper bounds and performance guarantees.
  H. Brendan McMahan and Maxim Likhachev and Geoffrey J. Gordon ICML 569-576 (2005)
  to dblp by dblp on 2006-04-25 00:00:00
  | URL | BibTeX  
• Online convex optimization in the bandit setting: gradient descent without a gradient.
  Abraham Flaxman and Adam Tauman Kalai and H. Brendan McMahan SODA 385-394 (2005)
  to dblp by dblp on 2006-02-10 00:00:00
  | URL | BibTeX  
• Fast Exact Planning in Markov Decision Processes.
  H. Brendan McMahan and Geoffrey J. Gordon ICAPS 151-160 (2005)
  to dblp by dblp on 2006-01-11 00:00:00
  | URL | BibTeX  
• Online Geometric Optimization in the Bandit Setting Against an Adaptive Adversary.
  H. Brendan McMahan and Avrim Blum COLT 109-123 (2004)
  to dblp by dblp on 2004-06-28 00:00:00
  | URL | BibTeX  
• Multi-source spanning trees: algorithms for minimizing source eccentricities.
  H. Brendan McMahan and Andrzej Proskurowski Discrete Applied Mathematics 137 213-222 (2004)
  to dblp by dblp on 2004-05-12 00:00:00
  | URL | BibTeX  
• Planning in the Presence of Cost Functions Controlled by an Adversary.
  H. Brendan McMahan and Geoffrey J. Gordon and Avrim Blum ICML 536-543 (2003)
  to dblp by dblp on 2003-09-22 00:00:00
  | URL | BibTeX