We present an any-time concurrent probabilistic temporal planner that includes continuous and discrete uncertainties and metric functions. Our approach is a direct policy search t...
Human experience with interactive games will be enhanced if the software agents that play the game learn from their failures. Techniques such as reinforcement learning provide one...
In this paper we describe a system called ViGLS (Visualization of Game Log Summaries) that generates summaries of gameplay sessions from game logs. ViGLS automatically produces vi...
We address the problem of coordinating the plans and schedules for a team of agents in an uncertain and dynamic environment. Bounded rationality, bounded communication, subjectivi...
In this paper, we report on a new solver for large instances of the Disjunctive Temporal Problem (DTP). Our solver is based primarily on the idea of employing "compact" ...