In this paper, we present an integrated planning and robotic architecture that actively directs an agent engaged in an urban search and rescue (USAR) scenario. We describe three s...
Kartik Talamadupula, J. Benton, Paul W. Schermerho...
Despite the recent advances in planning with MDPs, the problem of generating good policies is still hard. This paper describes a way to generate policies in MDPs by (1) determiniz...
This paper presents two models of goal generation which enable a motivated autonomous agent to generate goals in response to changes in its underlying drives or motivations, while...
Approximate inference in dynamic systems is the problem of estimating the state of the system given a sequence of actions and partial observations. High precision estimation is fu...
In our research we study rational agents which learn how to choose the best conditional, partial plan in any situation. The agent uses an incomplete symbolic inference engine, emp...