Approximate Inference and Stochastic Optimal Control

نویسندگان

  • Konrad Rawlik
  • Marc Toussaint
  • Sethu Vijayakumar
چکیده

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.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

On Stochastic Optimal Control and Reinforcement Learning by Approximate Inference (Extended Abstract)

We present a reformulation of the stochastic optimal control problem in terms of KL divergence minimisation, not only providing a unifying perspective of previous approaches in this area, but also demonstrating that the formalism leads to novel practical approaches to the control problem. Specifically, a natural relaxation of the dual formulation gives rise to exact iterative solutions to the f...

متن کامل

An optimal method based on rationalized Haar wavelet for approximate answer of stochastic Ito-Volterra integral equations

This article proposes an optimal method for approximate answer of stochastic Ito-Voltrra integral equations, via rationalized Haar functions and their stochastic operational matrix of integration. Stochastic Ito-voltreea integral equation is reduced to a system of linear equations. This scheme is applied for some examples. The results show the efficiency and accuracy of the method.

متن کامل

Optimal Relief Order Quantity under Stochastic Demand and Lead-time

In this paper, a newsboy model is developed under uniformly distributed lead-time and demand that is an appropriate assumption in obtaining optimal relief inventory of humanitarian disasters. It is noteworthy that limited historical data are in hand on relief operations. Hence, analytical and approximate solutions for optimal relief order quan­tity were derived. The effect of lead-time uncertai...

متن کامل

On Probabilistic Inference Approaches to Stochastic Optimal Control

While stochastic optimal control, together with associate formulations like Reinforcement Learning, provides a formal approach to, amongst other, motor control, it remains computationally challenging for most practical problems. This thesis is concerned with the study of relations between stochastic optimal control and probabilistic inference. Such dualities – exemplified by the classical Kalma...

متن کامل

Graphical Model Inference in Optimal Control of Stochastic Multi-Agent Systems

In this article we consider the issue of optimal control in collaborative multi-agent systems with stochastic dynamics. The agents have a joint task in which they have to reach a number of target states. The dynamics of the agents contains additive control and additive noise, and the autonomous part factorizes over the agents. Full observation of the global state is assumed. The goal is to mini...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • CoRR

دوره abs/1009.3958  شماره 

صفحات  -

تاریخ انتشار 2010