15 search results - page 1 / 3 » On the Worst-Case Analysis of Temporal-Difference Learning A... |
ICML
1994
IEEE
13 years 8 months ago
1994
IEEE
AI
1998
Springer
13 years 4 months ago
1998
Springer
The absolute loss is the absolute difference between the desired and predicted outcome. This paper demonstrates worst-case upper bounds on the absolute loss for the Perceptron le...
NIPS
2004
13 years 6 months ago
2004
We provide a worst-case analysis of selective sampling algorithms for learning linear threshold functions. The algorithms considered in this paper are Perceptron-like algorithms, ...
JMLR
2006
13 years 5 months ago
2006
A selective sampling algorithm is a learning algorithm for classification that, based on the past observed data, decides whether to ask the label of each new instance to be classi...
ML
2002
ACM
13 years 4 months ago
2002
ACM
We provide an analytical comparison between discounted and average reward temporal-difference (TD) learning with linearly parameterized approximations. We first consider the asympt...