Back to Results
First PageMeta Content
Control theory / Kalman filter / Robot control / Singular value decomposition / Reinforcement learning / Dynamical system / Μ operator / Normal distribution / Algebra / Mathematics / Markov models


Predictive State Temporal Difference Learning Geoffrey J. Gordon Machine Learning Department Carnegie Mellon University Pittsburgh, PA 15213
Add to Reading List

Document Date: 2011-01-19 12:04:47

Open Document

File Size: 517,35 KB

Share Result on Facebook

City

San Francisco / New York / /

Company

Neural Information Processing Systems / Cambridge University Press / Johns Hopkins University Press / Discrete Event Dynamic Systems / /

Country

United States / /

/

Facility

Byron Boots Machine Learning Department Carnegie Mellon University / Predictive State Temporal Difference Learning Geoffrey J. Gordon Machine Learning Department Carnegie Mellon University / /

IndustryTerm

consistent algorithm / subspace identification algorithm / predictive compression operator / Linear least-squares algorithms / dynamical systems / model-free algorithm / approximation algorithms / spectral algorithm / temporal difference algorithms / combinatorial search / learning algorithm / learning algorithms / /

MarketIndex

set 220 / /

Organization

UCLA / Cambridge University / Byron Boots Machine Learning Department Carnegie Mellon University Pittsburgh / The Johns Hopkins University / U.S. Securities and Exchange Commission / Predictive State Temporal Difference Learning Geoffrey J. Gordon Machine Learning Department Carnegie Mellon University Pittsburgh / /

Person

Sajid M. Siddiqi / Michael James / Harold Hotelling / Geoffrey J. Gordon / J. Zico Kolter / Michael L. Littman / Gavin Taylor / Tsitsiklis Roy / Byron Boots / Justin A. Boyan / Van Roy / Craig Boutilier / Benjamin Van Roy / Gregory C. Reinsel / LARS-TD PSTD / Matthew Rosencrantz / Steven J. Bradtke / Daniel Hsu / Pascal Poupart / Satinder Singh / Morgan Kaufmann / John N. Tsitsiklis / Benjamin Roy / Andrew G. Barto / Lihong Li / Gene H. Golub / David Choi / Tong Zhang / Michael Littman / Andrew Y. Ng / Matthew Rudary / Sebastian Thrun / Michael R. James / Michail G. Lagoudakis / P. Van Overschee / Ton Wessling / Rajabather Palani Velu / Ronald Parr / Nikos A. Vlassis / Sham Kakade / Richard Sutton / Herbert Jaeger / Christopher Painter-Wakefield / /

/

Position

VP / Rt / continuing forward / Pk Rt / immediate rewards Rt / /

ProvinceOrState

British Columbia / New York / Pennsylvania / California / /

PublishedMedium

Machine Learning / /

Technology

Linear least-squares algorithms / PSTD learning algorithm / spectral algorithm / model-free algorithm / PSTD algorithm / statistically consistent algorithm / model-based algorithm / Machine Learning / learning algorithm / 3 algorithms / artificial intelligence / temporal difference algorithms / approximation algorithms / simulation / subspace identification algorithm / /

SocialTag