We introduce the first algorithm for off-policy temporal-difference learning that is stable with linear function approximation. Off-policy learning is of interest because it forms...
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
Doina Precup, Richard S. Sutton, Satinder P. Singh
We study in this paper the Web forum crawling problem, which is a very fundamental step in many Web applications, such as search engine and Web data mining. As a typical user-crea...
Rui Cai, Jiang-Ming Yang, Wei Lai, Yida Wang, Lei ...
The asymmetry of activity in virtual communities is of great interest. While participation in the activities of virtual communities is crucial for a community's survival and ...
Although originally designed for large-scale electronic publishing, XML plays an increasingly important role in the exchange of data on the Web. In fact, it is expected that XML w...