—We propose various logical semantics for change of awareness. The setting is that of multiple agents that may become aware of facts or other agents, or forget about them. We mod...
Multiagent probabilistic reasoning with multiply sectioned Bayesian networks requires interfacing agent subnets (the modeling task) subject to a set of conditions. To specify the ...
Multiple instance learning (MIL) is a branch of machine learning that attempts to learn information from bags of instances. Many real-world applications such as localized content-...
In this paper we present a rich decision model for intelligent agents involved in multi issue negotiations. The model, grounded on information theory, takes into account the aspec...
We contribute Policy Reuse as a technique to improve a reinforcement learning agent with guidance from past learned similar policies. Our method relies on using the past policies ...