The problem of reinforcement learning in large factored Markov decision processes is explored. The Q-value of a state-action pair is approximated by the free energy of a product o...
Abstract-- In the proxy approach to Service Oriented Computing, a service advertises a proxy, which is searched for, retrieved and used by interested clients as a local handle to t...
Rohan Sen, Radu Handorean, Gregory Hackmann, Gruia...
- Many real-time distributed collaborative applications are emerging that require exchange of critical sensor data among geographically distant end users under resource-constrained...
Tarun Banka, Panho Lee, Anura P. Jayasumana, Jim K...
Code coverage is a common aid in the testing process. It is generally used for marking the source code segments that were executed and, more importantly, those that were not execu...
Yoram Adler, Eitan Farchi, Moshe Klausner, Dan Pel...
Although the ant metaphor has been successfully applied to routing of data packets both in wireless and fixed networks, little is known yet about its appropriateness for search i...