pith. sign in

arxiv: 1009.3958 · v1 · pith:WLNGO4QGnew · submitted 2010-09-20 · 💻 cs.LG · stat.ML

Approximate Inference and Stochastic Optimal Control

classification 💻 cs.LG stat.ML
keywords problemcontroloptimalstochasticapproximateinferencemethodsnovel
0
0 comments X
read the original abstract

We propose a novel reformulation of the stochastic optimal control problem as an approximate inference problem, demonstrating, that such a interpretation leads to new practical methods for the original problem. In particular we characterise a novel class of iterative solutions to the stochastic optimal control problem based on a natural relaxation of the exact dual formulation. These theoretical insights are applied to the Reinforcement Learning problem where they lead to new model free, off policy methods for discrete and continuous problems.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.