Stochastic control as an inference problem
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Zoubin Ghahramani.
Stochastic optimal control theory deals with the problem to compute an
optimal set of actions to attain some future goal. Examples are found
in many contexts such as motor control tasks for robotics, planning and
scheduling tasks or managing a financial portfolio. The computation of
the optimal control is typically very difficult due to the size of the
state space and the stochastic nature of the problem.
We introduce a class of stochastic optimal control problems that can
be mapped onto a probabilistic inference problem. This duality between
control and inference is wellknown. The novel aspect of the present
formulation is that the optimal solution is given by the minimum of a
free energy and the link to graphical model inference. We can thus apply principled approximations such as the belief propagation or the Cluster Variation method to obtain efficient approximations.
We will illustrate the method for the task stacking blocks. If time permits we will discuss distributed (agent) solutions and comment on the partial observable case.
This talk is part of the Machine Learning @ CUED series.
This talk is included in these lists:
Note that exdirectory lists are not shown.
