This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. This approach is based on a direct approximation of AIXI, a Bayesian...
Joel Veness, Kee Siong Ng, Marcus Hutter, David Si...
Based on a minimal set of axioms we introduce a general integral which can be defined on arbitrary measurable spaces. It acts on measures which are only (finite) monotone set fu...
We present a general framework for defining nonmonotonic systems based on the notion of preferred maximal consistent subsets of the premises. This framework subsumes David Poole...
Parallel platforms are becoming ubiquitous with modern computing systems. Many parallel applications attempt to avoid locks in order to achieve high responsiveness, aid scalabilit...
Abstract. We present a generic approach to readable formal proof documents, called Intelligible semi-automated reasoning (Isar). It addresses the major problem of existing interact...