Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...
Ruben Martinez-Cantin, Nando de Freitas, Arnaud Do...
We consider the problem of efficiently learning optimal control policies and value functions over large state spaces in an online setting in which estimates must be available afte...
This paper describes the development of QuestionBank, a corpus of 4000 parseannotated questions for (i) use in training parsers employed in QA, and (ii) evaluation of question par...
Although some guidelines (e.g., based on architectural principles) have been proposed for designing Virtual Environments (VEs), several usability problems can be identified only b...
Coupling measures have important applications in software development and maintenance. They are used to reason about the structural complexity of software and have been shown to p...