Material Detail

An efficient approach to stochastic optimal control

An efficient approach to stochastic optimal control

This video was recorded at Workshop on Approximate Inference in Stochastic Processes and Dynamical Systems, Cumberland Lodge 2008. Stochastic optimal control theory is a principled approach to compute optimal actions with delayed rewards. The use of this approach in AI and machine learning has been limited due to the computational intractabilities. In this talk, I introduce a class of control problems where the intractabilities appear as the computation of a partition sum, as in a statistical mechanical system. This opens the possibility to study phase transitions and to apply exisiting approximation methods such as BP and the variational method to optimal control theory. The talk gives a gentle introduction into control theory and illustrates these new phenomena with a number of examples.

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.