Sciweavers

567 search results - page 100 / 114
» Regularized Policy Iteration
Sort
View
ECAI
2006
Springer
13 years 11 months ago
Least Squares SVM for Least Squares TD Learning
Abstract. We formulate the problem of least squares temporal difference learning (LSTD) in the framework of least squares SVM (LS-SVM). To cope with the large amount (and possible ...
Tobias Jung, Daniel Polani
ICSE
2000
IEEE-ACM
13 years 11 months ago
Dragonfly: linking conceptual and implementation architectures of multiuser interactive systems
Software architecture styles for developing multiuser applications are usually defined at a conceptual level, abstracting such low-level issues of distributed implementation as co...
Gary E. Anderson, T. C. Nicholas Graham, Timothy N...
AAAI
2007
13 years 9 months ago
Thresholded Rewards: Acting Optimally in Timed, Zero-Sum Games
In timed, zero-sum games, the goal is to maximize the probability of winning, which is not necessarily the same as maximizing our expected reward. We consider cumulative intermedi...
Colin McMillen, Manuela M. Veloso
AAAI
2010
13 years 9 months ago
Decision-Theoretic Control of Crowd-Sourced Workflows
Crowd-sourcing is a recent framework in which human intelligence tasks are outsourced to a crowd of unknown people ("workers") as an open call (e.g., on Amazon's Me...
Peng Dai, Mausam, Daniel S. Weld
DGO
2010
148views Education» more  DGO 2010»
13 years 9 months ago
Supporting agile modeling through experimentation in an integrated urban simulation framework
Decisions regarding major urban transportation projects and land use policies are frequently political and controversial, as well as having significant economic, social, and envir...
Travis Kriplean, Alan Borning, Paul Waddell, Chris...