English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Policy gradient methods

Peters, J. (2010). Policy gradient methods. Scholarpedia, 5(11), 3698. doi:10.4249/scholarpedia.3698.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-BD68-3 Version Permalink: http://hdl.handle.net/21.11116/0000-0002-68BC-6
Genre: Journal Article

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Peters, J1, 2, Author              
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: Policy gradient methods are a type of reinforcement learning techniques that rely upon optimizing parametrized policies with respect to the expected return (long-term cumulative reward) by gradient descent. They do not suffer from many of the problems that have been marring traditional reinforcement learning approaches such as the lack of guarantees of a value function, the intractability problem resulting from uncertain state information and the complexity arising from continuous states actions.

Details

show
hide
Language(s):
 Dates: 2010-11
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.4249/scholarpedia.3698
BibTex Citekey: 6940
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Scholarpedia
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 5 (11) Sequence Number: - Start / End Page: 3698 Identifier: -