This paper studies efficient learning with respect to mind changes. Our starting point is the idea that a learner that is efficient with respect to mind changes minimizes mind cha...
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...
This paper treats the problem of managing personal tasks, through an adaptation of the Squeaky Wheel Optimization (SWO) framework, enhanced with powerful heuristics and full const...
Borodin, Nielsen and Rackoff [5] proposed a framework for ing the main properties of greedy-like algorithms with emphasis on scheduling problems, and Davis and Impagliazzo [6] ext...
Over the last few years, a few approaches have been proposed aiming to combine genetic and evolutionary computation (GECCO) with inductive logic programming (ILP). The underlying r...