Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

12

ICML
2010
IEEE

favoriteEmaildiscussreport

198views Machine Learning» more ICML 2010»

Approximate Predictive Representations of Partially Observable Systems

13 years 2 months ago

Approximate Predictive Representations of Partially Observable Systems

Download www.icml2010.org

We provide a novel view of learning an approximate model of a partially observable environment from data and present a simple implemenf the idea. The learned model abstracts away unnecessary details of the agent's experience and focuses only on making certain predictions of interest. We illustrate our approach in small computational examples, demonstrating the data efficiency of the algorithm.

Monica Dinculescu, Doina Precup

Real-time Traffic

Approximate Model | ICML 2010 | Machine Learning | Observable Environment | Small Computational Examples |

claim paper

Related Content

» A Predictive Model for Imitation Learning in Partially Observable Environments

» Computing Optimal Policies for Partially Observable Decision Processes Using Compact Repre...

» An Online Spectral Learning Algorithm for Partially Observable Nonlinear Dynamical Systems

» On discovery and learning of models with predictive representations of state for agents wi...

» A Planning Algorithm for Predictive State Representations

» Efficiently learning linearlinear exponential family predictive representations of state

» Improving Approximate Value Iteration Using Memories and Predictive State Representations

» Learning low dimensional predictive representations

» Predictive Representations of State

Post Info
More Details (n/a)

Added	12 Feb 2011
Updated	12 Feb 2011
Type	Journal
Year	2010
Where	ICML
Authors	Monica Dinculescu, Doina Precup

Comments (0)