We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorit...
Regulations in various countries permit the reuse of health information without patient authorization provided the data is "de-identified". In the United States, for ins...
r The lack of a versatile software tool for parallel program development has been one of the major obstacles for exploiting the potential of high-performance architectures. In this...
We consider the problem of optimizing multilabel MRFs, which is in general NP-hard and ubiquitous in low-level computer vision. One approach for its solution is to formulate it as...
Pushmeet Kohli, Alexander Shekhovtsov, Carsten Rot...
In this paper, we apply an evolutionary algorithm to learning behavior on a novel, interesting task to explore the general issue of learning e ective behaviors in a complex enviro...