Approximate linear programming (ALP) offers a promising framework for solving large factored Markov decision processes (MDPs) with both discrete and continuous states. Successful ...
We prove two main results on how arbitrary linear threshold functions f(x) = sign(w · x − θ) over the n-dimensional Boolean hypercube can be approximated by simple threshold f...
Belief propagation on cyclic graphs is an efficient algorithm for computing approximate marginal probability distributions over single nodes and neighboring nodes in the graph. I...
Synchronous reinforcement learning (RL) algorithms with linear function approximation are representable as inhomogeneous matrix iterations of a special form (Schoknecht & Merk...
We consider linear fixed point equations and their approximations by projection on a low dimensional subspace. We derive new bounds on the approximation error of the solution, whi...