This paper presents the dynamics of multi-agent reinforcement learning in multiple state problems. We extend previous work that formally modelled the relation between reinforcemen...
We address the problem of collecting a database of "common-sense facts" using a computer game. Informally, a common-sense fact is a true statement about the world that i...
We present a coreference resolver called BABAR that uses contextual role knowledge to evaluate possible antecedents for an anaphor. BABAR uses information extraction patterns to i...
We present a pilot for a student consultancy service offering students the opportunity to work with internal and external clients on real life projects to learn and enhance trans...
Classically, an approach to the multiagent policy learning supposed that the agents, via interactions and/or by using preliminary knowledge about the reward functions of all playe...