Sciweavers

250 search results - page 37 / 50
» Learning action effects in partially observable domains
Sort
View
ICML
2000
IEEE
15 years 10 months ago
Version Space Algebra and its Application to Programming by Demonstration
Machine learning research has been very successful at producing powerful, broadlyapplicable classification learners. However, many practical learning problems do not fit the class...
Tessa A. Lau, Pedro Domingos, Daniel S. Weld
SIGECOM
2006
ACM
139views ECommerce» more  SIGECOM 2006»
15 years 3 months ago
Playing games in many possible worlds
In traditional game theory, players are typically endowed with exogenously given knowledge of the structure of the game—either full omniscient knowledge or partial but fixed in...
Matt Lepinski, David Liben-Nowell, Seth Gilbert, A...
NIPS
2003
14 years 11 months ago
Extending Q-Learning to General Adaptive Multi-Agent Systems
Recent multi-agent extensions of Q-Learning require knowledge of other agents’ payoffs and Q-functions, and assume game-theoretic play at all times by all other agents. This pap...
Gerald Tesauro
GPEM
2008
128views more  GPEM 2008»
14 years 9 months ago
Coevolutionary bid-based genetic programming for problem decomposition in classification
In this work a cooperative, bid-based, model for problem decomposition is proposed with application to discrete action domains such as classification. This represents a significan...
Peter Lichodzijewski, Malcolm I. Heywood
74
Voted
AAAI
2012
13 years 3 hour ago
Security Games for Controlling Contagion
Many strategic actions carry a ‘contagious’ component beyond the immediate locale of the effort itself. Viral marketing and peacekeeping operations have both been observed to ...
Jason Tsai, Thanh H. Nguyen, Milind Tambe