Policy search by dynamic programming

Policy search by dynamic programming (2003)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by J. Andrew Bagnell , Andrew Y. Ng , Sham Kakade , Jeff Schneider

Venue:	in Advances in Neural Information Processing Systems
Citations:	38 - 2 self

BibTeX

@INPROCEEDINGS{Bagnell03policysearch,
    author = {J. Andrew Bagnell and Andrew Y. Ng and Sham Kakade and Jeff Schneider},
    title = {Policy search by dynamic programming},
    booktitle = {in Advances in Neural Information Processing Systems},
    year = {2003},
    pages = {16},
    publisher = {MIT Press}
}

Years of Citing Articles

Bookmark

OpenURL

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. 1

Citations

No citations identified.