COLT
2000
Springer
13 years 9 months ago
2000
Springer
We give the first rigorous upper bounds on the error of temporal difference (td) algorithms for policy evaluation as a function of the amount of experience. These upper bounds pr...
COLT
2000
Springer
13 years 9 months ago
2000
Springer
COLT
2000
Springer
13 years 9 months ago
2000
Springer
We combine the results of [13] and [8] and derive a continuous variant of a large class of drifting games. Our analysis furthers the understanding of the relationship between boos...
COLT
2000
Springer
13 years 9 months ago
2000
Springer
COLT
2000
Springer
13 years 9 months ago
2000
Springer
Output coding is a general framework for solving multiclass categorization problems. Previous research on output codes has focused on building multiclass machines given predefine...
COLT
2000
Springer
13 years 9 months ago
2000
Springer
COLT
2000
Springer
13 years 9 months ago
2000
Springer
We study model selection strategies based on penalized empirical loss minimization. We point out a tight relationship between error estimation and data-based complexity penalizatio...
COLT
2000
Springer
13 years 9 months ago
2000
Springer
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process ( ¢¡¤£¦¥§ ), and focus on gradient ascent approache...
COLT
2000
Springer
13 years 9 months ago
2000
Springer
COLT
2000
Springer
13 years 9 months ago
2000
Springer
We investigate the computational complexity of the task of detecting dense regions of an unknown distribution from un-labeled samples of this distribution. We introduce a formal l...