Foundations of Robotics Seminar, February 21, 2007
Time and Place | Seminar
Abstract | Speaker Biography | Presentation
Slides | Speaker Appointments
Randomly Sampling Actions In
Dynamic Programming
Chris Atkeson
NSH 1507
Refreshments 4:15 pm
Talk 4:30 pm
We describe an
approach towards reducing the curse of dimensionality for deterministic dynamic
programming with continuous actions by randomly sampling actions while computing
a steady state value function and policy. This approach results in globally
optimized actions, without searching over a discretized
multidimensional grid.
We present results
on finding time invariant control laws for two, four, and six dimensional
deterministic swing up problems with up to 480 million
discretized states.
For
appointments, please contact Chris Atkeson.
The Robotics
Institute is part of the School of
Computer Science, Carnegie Mellon University.