TR2003-91

Non-Linear Stochastic Control in Continuous State Spaces by Exact Integration in Bellman's Equations


Abstract:

We present an algorithm for sequential control of tasks with non-linear stochastic dynamics in continuous state spaces, characterized by inhomogeneous noise. The algorithm performs approximate value iteration steps on a select set of prototypical states whose cost-to-go is approximated by means of a radial-basis function network. This allows the resulting Bellman's equations to be integrated exactly with respect to the transition densities of a large class of stochastic dynamical systems, resulting in a fast and efficient modified value-iteration procedure.

 

  • Related News & Events

    •  NEWS    ICAPS 2003: 2 publications by Matthew Brand and Daniel Nikovski
      Date: June 9, 2003
      Where: International Conference on Automated Planning and Scheduling (ICAPS)
      MERL Contacts: Matthew Brand; Daniel N. Nikovski
      Brief
      • The papers "Decision-Theoretic Group Elevator Scheduling" by Nikovski, D. and Brand, M. and "Non-Linear Stochastic Control in Continuous State Spaces by Exact Integration in Bellman\'s Equations" by Nikovski, D. and Brand, M. were presented at the International Conference on Automated Planning and Scheduling (ICAPS).
    •