2006 |
9 | EE | Daniela Pucci de Farias,
Nimrod Megiddo:
Combining expert advice in reactive environments.
J. ACM 53(5): 762-799 (2006) |
2005 |
8 | | Ion Muslea,
Virginia Dignum,
Daniel D. Corkill,
Catholijn M. Jonker,
Frank Dignum,
Silvia Coradeschi,
Alessandro Saffiotti,
Dan Fu,
Jeff Orkin,
William Cheetham,
Kai Goebel,
Piero P. Bonissone,
Leen-Kiat Soh,
Randolph M. Jones,
Robert E. Wray III,
Matthias Scheutz,
Daniela Pucci de Farias,
Shie Mannor,
Georgios Theocharous,
Doina Precup,
Bamshad Mobasher,
Sarabjot S. Anand,
Bettina Berendt,
Andreas Hotho,
Hans W. Guesgen,
Michael T. Rosenstein,
Mohammad Ghavamzadeh:
The Workshop Program at the Nineteenth National Conference on Artificial Intelligence.
AI Magazine 26(1): 103-108 (2005) |
2004 |
7 | EE | Daniela Pucci de Farias,
Benjamin Van Roy:
A Cost-Shaping LP for Bellman Error Minimization with Performance Guarantees.
NIPS 2004 |
6 | EE | Daniela Pucci de Farias,
Nimrod Megiddo:
Exploration-Exploitation Tradeoffs for Experts Algorithms in Reactive Environments.
NIPS 2004 |
5 | EE | Daniela Pucci de Farias,
Benjamin Van Roy:
On Constraint Sampling in the Linear Programming Approach to Approximate Dynamic Programming.
Math. Oper. Res. 29(3): 462-478 (2004) |
2003 |
4 | EE | Daniela Pucci de Farias,
Nimrod Megiddo:
How to Combine Expert (and Novice) Advice when Actions Impact the Environment?
NIPS 2003 |
2002 |
3 | EE | Daniela Pucci de Farias,
Benjamin Van Roy:
Approximate Linear Programming for Average-Cost Dynamic Programming.
NIPS 2002: 1587-1594 |
2001 |
2 | EE | Daniela Pucci de Farias,
Benjamin Van Roy:
Approximate Dynamic Programming via Linear Programming.
NIPS 2001: 689-695 |
2000 |
1 | | Daniela Pucci de Farias,
Benjamin Van Roy:
Fixed Points of Approximate Value Iteration and Temporal-Difference Learning.
ICML 2000: 207-214 |