A Scalable Method for Solving High-Dimensional Continuous POMDPs Using Local Approximation

Details A Scalable Method for Solving High-Dimensional Continuous POMDPs Using Local Approximation A Scalable Method for Solving High-Dimensional Continuous POMDPs Using Local Approximation

2012-03-15

arxiv.org/abs/1203.3477v1

Computer Science

Artificial Intelligence

Appears in Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI2010)

Scientific paper

Partially-Observable Markov Decision Processes (POMDPs) are typically solved by finding an approximate global solution to a corresponding belief-MDP. In this paper, we offer a new planning algorithm for POMDPs with continuous state, action and observation spaces. Since such domains have an inherent notion of locality, we can find an approximate solution using local optimization methods. We parameterize the belief distribution as a Gaussian mixture, and use the Extended Kalman Filter (EKF) to approximate the belief update. Since the EKF is a first-order filter, we can marginalize over the observations analytically. By using feedback control and state estimation during policy execution, we recover a behavior that is effectively conditioned on incoming observations despite the unconditioned planning. Local optimization provides no guarantees of global optimality, but it allows us to tackle domains that are at least an order of magnitude larger than the current state-of-the-art. We demonstrate the scalability of our algorithm by considering a simulated hand-eye coordination domain with 16 continuous state dimensions and 6 continuous action dimensions.

Affiliated with

Also associated with

No associations

Rating

A Scalable Method for Solving High-Dimensional Continuous POMDPs Using Local Approximation does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A Scalable Method for Solving High-Dimensional Continuous POMDPs Using Local Approximation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Scalable Method for Solving High-Dimensional Continuous POMDPs Using Local Approximation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-32131