2007 |
10 | | H. Brendan McMahan,
Geoffrey J. Gordon:
A Unification of Extensive-Form Games and Markov Decision Processes.
AAAI 2007: 86-93 |
9 | EE | Brent Bryan,
H. Brendan McMahan,
Chad M. Schafer,
Jeff G. Schneider:
Efficiently computing minimax expected-size confidence regions.
ICML 2007: 97-104 |
8 | EE | Andreas Krause,
H. Brendan McMahan,
Carlos Guestrin,
Anupam Gupta:
Selecting Observations against Adversarial Objectives.
NIPS 2007 |
2005 |
7 | | H. Brendan McMahan,
Geoffrey J. Gordon:
Fast Exact Planning in Markov Decision Processes.
ICAPS 2005: 151-160 |
6 | EE | H. Brendan McMahan,
Maxim Likhachev,
Geoffrey J. Gordon:
Bounded real-time dynamic programming: RTDP with monotone upper bounds and performance guarantees.
ICML 2005: 569-576 |
5 | EE | Abraham Flaxman,
Adam Tauman Kalai,
H. Brendan McMahan:
Online convex optimization in the bandit setting: gradient descent without a gradient.
SODA 2005: 385-394 |
2004 |
4 | EE | H. Brendan McMahan,
Avrim Blum:
Online Geometric Optimization in the Bandit Setting Against an Adaptive Adversary.
COLT 2004: 109-123 |
3 | EE | Abraham Flaxman,
Adam Tauman Kalai,
H. Brendan McMahan:
Online convex optimization in the bandit setting: gradient descent without a gradient
CoRR cs.LG/0408007: (2004) |
2 | EE | H. Brendan McMahan,
Andrzej Proskurowski:
Multi-source spanning trees: algorithms for minimizing source eccentricities.
Discrete Applied Mathematics 137(2): 213-222 (2004) |
2003 |
1 | | H. Brendan McMahan,
Geoffrey J. Gordon,
Avrim Blum:
Planning in the Presence of Cost Functions Controlled by an Adversary.
ICML 2003: 536-543 |