Partially-observable Markov decision processes (POMDPs) provide a powerful model for sequential decision-making problems with partially-observed state and are known to have (appro...
We present a deterministic approximation algorithm to compute logarithm of the number of `good' truth assignments for a random k-satisfiability (k-SAT) formula in polynomial ...
We show that the first-order theory of structural subtyping of non-recursive types is decidable. Let be a language consisting of function symbols (representing type constructors)...
as a tree which specifies the presentation in an abstract, machineindependent way. This specification is created and edited using an authoring system; it is mapped to a particula...
Guido van Rossum, Jack Jansen, K. Sjoerd Mullender...
This paper describes a computationally feasible approximation to the AIXI agent, a universal reinforcement learning agent for arbitrary environments. AIXI is scaled down in two ke...
Joel Veness, Kee Siong Ng, Marcus Hutter, William ...