Recent research has seen the proposal of several new inductive principles designed specifically to avoid the problems associated with maximum likelihood learning in models with in...
Benjamin Marlin, Kevin Swersky, Bo Chen, Nando de ...
As organization-based multiagent systems are applied to more complex problems, configuring and tuning the systems can become nearly as complex as the original problem a system wa...
Scott J. Harmon, Scott A. DeLoach, Robby, Doina Ca...
Designing the dialogue policy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a di...
Satinder P. Singh, Diane J. Litman, Michael J. Kea...
: On-line learning is one of the emerging needs of the information age. Access to education is going to become crucial for the success of our information society. Therefore a lot o...
The purpose of this study is to explore how student competition using the tit-for-tat strategy could be remedied with a minimum design change in order to support student to collabo...