Off-policy reinforcement learning with Gaussian processes
Name
How_Off-policy.pdf
Size
562.6 KB
Format
Adobe PDF
Checksum (MD5)
ff342a3ec11f413ca9399055f6cc5bf8
Author(s)
Chowdhary, Girish
Liu, Miao
Grande, Robert
Walsh, Thomas
How, Jonathan P.
Carin, Lawrence
Date Issued
July 2014
Journal
IEEE/CAA Journal of Automatica Sinica
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Chowdhary, Girish, Miao Liu, Robert Grande, Thomas Walsh, Jonathan How, and Lawrence Carin. "Off-policy reinforcement learning with Gaussian processes." IEEE/CAA Journal of Automatica Sinica, Vol. 1, No. 3, July 2014.
Version
Author's final manuscript
Abstract
An off-policy Bayesian nonparameteric approximate reinforcement learning framework, termed as GPQ, that employs a Gaussian processes (GP) model of the value (Q) function is presented in both the batch and online settings. Sufficient conditions on GP hyperparameter selection are established to guarantee convergence of off-policy GPQ in the batch setting, and theoretical and practical extensions are provided for the online case. Empirical results demonstrate GPQ has competitive learning speed in addition to its convergence guarantees and its ability to automatically choose its own bases locations.
MIT Department
Massachusetts Institute of Technology. Aerospace Controls Laboratory
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/JAS.2014.7004680
