Memory-bounded techniques have shown great promise in solving complex multi-agent planning problems modeled as DEC-POMDPs. Much of the performance gains can be attributed to pruni...
This paper presents a model of neural network embodiment of intentions and planning mechanisms for autonomous agents. The model bridges the dichotomy of symbolic and non-symbolic ...
This paper summarizes recent work reported at ICAPS on applying artificial intelligence techniques to the control of production printing equipment. Like many other real-world appl...
The paper deals with the problem of computing schedules for multi-threaded real-time programs. In [14] we introduced a scheduling method based on the geometrization of PV programs...
Partially observable Markov decision processes (POMDPs) are an intuitive and general way to model sequential decision making problems under uncertainty. Unfortunately, even approx...
Tao Wang, Pascal Poupart, Michael H. Bowling, Dale...