Back to Results
First PageMeta Content
Reinforcement learning / CMA-ES / Dimensional analysis / Applied mathematics / Science / Estimation theory / Statistics / Measurement


Policy Gradients with Parameter-based Exploration for Control Frank Sehnke1 , Christian Osendorfer1 , Thomas R¨ uckstieß1 , 1 3
Add to Reading List

Document Date: 2009-11-26 21:08:11

Open Document

File Size: 1,68 MB

Share Result on Facebook

City

Aberdeen / San Francisco / Manno-Lugano / Cambridge / Beijing / New York / /

Company

Neural Information Processing Systems / MIT Press / Baxter / /

Country

Switzerland / Germany / Jordan / China / /

Facility

Institute of Applied Mechanics / Australian National University / Max-Planck Institute / /

IndustryTerm

statistical gradient-following algorithms / direct search / stochastic optimisation algorithms / typical solution / local mutation operator / policy gradient algorithms / online policy gradient learning / /

Organization

Federal Government / Faculty of Computer Science / Cognitive Science Society / MIT / Institute of Applied Mechanics / Max-Planck Institute for Biological Cybernetics T¨ / Australian National University / /

Person

Jan Peters / Mansour / Morgan Kaufmann / /

Position

Natural actor-critic / linear controller / rt / scalar reward rt / natural actor critic / head / controller / /

Product

ES / Franklin / /

ProgrammingLanguage

J / R / T / /

PublishedMedium

Machine Learning / /

Technology

policy gradient algorithms / transformed algorithm / PGPE algorithm / stochastic optimisation algorithms / Machine Learning / simulation / statistical gradient-following algorithms / Policy-Gradient Algorithms / /

URL

http /

SocialTag