Back to Results
First PageMeta Content
Statistical theory / Statistics / M-estimators / Econometrics / Science / Engineering / Maximum likelihood / Estimation theory / Dimensional analysis / Measurement


Parameter-exploring Policy Gradients Frank Sehnkea , Christian Osendorfera , Thomas R¨ uckstießa , Alex Gravesa , Jan Petersc , J¨ urgen Schmidhubera,b a
Add to Reading List

Document Date: 2010-07-15 09:01:14

Open Document

File Size: 882,82 KB

Share Result on Facebook

City

Aberdeen / Manno-Lugano / /

Company

Baxter / /

Country

Germany / Switzerland / Jordan / /

Facility

Max-Planck Institute / /

IndustryTerm

typical solution / above algorithms / local mutation operator / policy gradient algorithms / /

Movie

PGPE with REINFORCE / /

Organization

Faculty of Computer Science / Max-Planck Institute for Biological Cybernetics T¨ / US Federal Reserve / /

Person

Christian Osendorfera / Johnnie Ulbrich / Jan Petersc / Alex Gravesa / /

Position

rt / episodic natural actor critic / αT rT / scalar Markovian reward rt / head / linear controller / controller / /

Product

Franklin / /

ProgrammingLanguage

J / R / T / /

Technology

policy gradient algorithms / above algorithms / basic PGPE algorithm / improved algorithm / simulation / 6 Algorithm / PGPE algorithm / /

SocialTag