Policy gradient approaches are a powerful instrument for learning how to interact with the environment. Existing approaches have focused on propositional and continuous domains on...
Teachers working in robotics classes face a major problem: how to keep track on individual students’ or even small groups’ progress in a class of 30-40 students. An agency app...
Ilkka Jormanainen, Yuejun Zhang, Erkki Sutinen, Ki...
The main purpose of this work is to develop an intelligent tutor system coupled to a robotics virtual laboratory, in order to offer a tutored virtual learning environment. The stu...
Non-learning problem solvers have been applied to many interesting and complex domains. Experience-based learning techniques have been developed to augment the capabilities of cert...
Abstract. We present a method of learning a Bayesian model of a traveler moving through an urban environment. This technique is novel in that it simultaneously learns a unified mo...
Donald J. Patterson, Lin Liao, Dieter Fox, Henry A...