|
|
|
|
RI | Publications | Maximum Entropy Inverse Reinforcement Learning
|
|
Text only version of this site
Maximum Entropy Inverse Reinforcement Learning
B.D. Ziebart, A. Maas, J. Bagnell, and A.K. Dey
Proceeding of AAAI 2008, July, 2008.
Jump to: Download | Abstract | Notes | Text Reference | BibTeX Reference
| Download [Help] |
Adobe portable document format (pdf) [293 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 |
Recent research has shown the benefit of framing problems of imitation learning as solutions to Markov Decision Problems. This approach reduces the problem of learning to recovering a utility function that makes the behavior induced by a near-optimal policy closely mimic demonstrated behavior. In this work, we develop a probabilistic approach based on the principle of maximum entropy. Our approach provides a well-defined, globally normalized distribution over decisions, while providing the same performance guarantees as existing methods.
We develop our technique in the context of modeling real-world navigation and driving behaviors where collected data is inherently noisy and imperfect. Our probabilistic approach enables modeling of route preferences as well as a powerful new approach to inferring destinations and routes based on partial trajectories.
| Notes |
Sponsor: National Science Foundation
Associated lab/group: Human Sensing
Associated project: Quality of Life Technology Center
| Text Reference |
B.D. Ziebart, A. Maas, J. Bagnell, and A.K. Dey, "Maximum Entropy Inverse Reinforcement Learning," Proceeding of AAAI 2008, July, 2008.
| BibTeX Reference |
@inproceedings{Ziebart_2008_6055,
author = "Brian D. Ziebart and Andrew Maas and James (Drew) Bagnell and Anind K. Dey",
title = "Maximum Entropy Inverse Reinforcement Learning",
booktitle = "Proceeding of AAAI 2008",
month = "July",
year = "2008"
}