We build the generic methodology based on machine learning and reasoning to detect the patterns of interaction between conflicting agents, including humans and their assistants. L...
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 ...
We consider the problem of coordinating a team of agents engaged in executing a set of inter-dependent, geographically dispersed tasks in an oversubscribed and uncertain environme...
Laura Barbulescu, Zachary B. Rubinstein, Stephen F...
Practitioners interested in integrating mobile technology effectively into distance learning programs need to consider both the benefits and limitations of such devices. This pape...
The results of the latest International Probabilistic Planning Competition (IPPC-2008) indicate that the presence of dead ends, states with no trajectory to the goal, makes MDPs h...