Nonparametric Bayesian Policy Priors for Reinforcement Learning
Name
Roy_Nonparametric Bayesian.pdf
Size
175.44 KB
Format
Adobe PDF
Checksum (MD5)
7754ee2c85ed4f6aa0aac059fad3b9cd
Author(s)
Doshi-Velez, Finale P.
Wingate, David
Roy, Nicholas
Tenenbaum, Joshua B.
Date Issued
December 2010
Journal
Proceedings of the 24th Annual Conference on Neural Information Processing Systems, (NIPS 2010)
Publisher
Neural Information Processing Systems Foundation
Citation
Doshi-Velez, Finale, David Wingate, Nicholas Roy, and Joshua Tenenbaum. "Nonparametric Bayesian Policy Priors for Reinforcement Learning." Proceedings of the 24th Annual Conference on Neural Information Processing Systems, NIPS 2010, December 6-9, 2010, Vancouver, British Columbia.
Version
Author's final manuscript
Abstract
We consider reinforcement learning in partially observable domains where the agent can query an expert for
demonstrations. Our nonparametric Bayesian approach combines model knowledge, inferred from expert information and independent exploration, with policy knowledge inferred from expert trajectories. We introduce priors that bias the agent towards models with both simple representations and simple policies, resulting in improved policy and model learning.
MIT Department
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike 3.0
Persistent DSpace Link
DOI of Published Version
http://media.nips.cc/Conferences/2010/2010-NIPS-Conference-Program.pdf
