Improving the sample efficiency of reinforcement learning algorithms to scale up to larger and more realistic domains is a current research challenge in machine learning. Model-ba...
As organizations scale up, their collective knowledge increases, and the potential for serendipitous collaboration between members grows dramatically. However, finding people wit...
Decompiling low-level code to a high-level intermediate representation facilitates the development of analyzers, model checkers, etc. which reason about properties of the low-leve...
—Wireless sensor networks (WSN) built using current Berkeley Mica motes exhibit low reliability for packet delivery. There is anecdotal evidence of poor packet delivery rates fro...
JunSuk Shin, Umakishore Ramachandran, Mostafa H. A...
Distributed Partially Observable Markov Decision Problems (Distributed POMDPs) are a popular approach for modeling multi-agent systems acting in uncertain domains. Given the signi...
Pradeep Varakantham, Janusz Marecki, Yuichi Yabu, ...