RI | Publications | Policy Search by Dynamic Programming

Text only version of this site

Policy Search by Dynamic Programming
J. Bagnell, S. Kakade, A. Ng, and J. Schneider
Neural Information Processing Systems, MIT Press, Vol. 16, December, 2003.

Jump to: Download | Abstract | Notes | Text Reference | BibTeX Reference

Download [Help]

Adobe portable document format (pdf) [157 KB]
Compressed postscript (ps.gz) [73 KB]

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

We consider the policy search approach to reinforcement learning. We show that if a ``baseline distribution'' is given (indicating roughly how often we expect a good policy to visit each state), then we can derive a policy search algorithm that terminates in a finite number of steps, and for which we can provide non-trivial performance guarantees. We also demonstrate this algorithm on several grid-world POMDPs, a planar biped walking robot, and a double-pole balancing problem.

Notes

Associated lab/group: Auton Lab
Associated project: Auton Project

Text Reference

J. Bagnell, S. Kakade, A. Ng, and J. Schneider, "Policy Search by Dynamic Programming," Neural Information Processing Systems, MIT Press, Vol. 16, December, 2003.

BibTeX Reference

@inproceedings{Bagnell_2003_4485,
   author = "James (Drew) Bagnell and Sham Kakade and Andrew Ng and Jeff Schneider",
   title = "Policy Search by Dynamic Programming",
   booktitle = "Neural Information Processing Systems",
   month = "December",
   year = "2003",
   volume = "16",
   publisher = "MIT Press"
}