English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning

Ahilan, S., & Dayan, P. (2019). Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning. In Annual Conference of the American Library Association (ALA 2019) (pp. 1-5).

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0005-4B86-0 Version Permalink: http://hdl.handle.net/21.11116/0000-0005-4B87-F
Genre: Conference Paper

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Ahilan, S, Author
Dayan, P1, 2, Author              
Affiliations:
1Department of Computational Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_3017468              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: We investigate how reinforcement learning agents can learn tocooperate. Drawing inspiration from human societies, in whichsuccessful coordination of many individuals is often facilitated byhierarchical organisation, we introduce Feudal Multi-agent Hierar-chies (FMH). In this framework, a ‘manager’ agent, which is taskedwith maximising the environmentally-determined reward func-tion, learns to communicate subgoals to multiple, simultaneously-operating, ‘worker’ agents. Workers, which are rewarded for achiev-ing managerial subgoals, take concurrent actions in the world. Weoutline the structure of FMH and demonstrate its potential for de-centralised learning and control. We find that, given an adequate setof subgoals from which to choose, FMH performs, and particularlyscales, substantially better than cooperative approaches that use ashared reward function.

Details

show
hide
Language(s):
 Dates: 2019-06
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: Annual Conference of the American Library Association (ALA 2019)
Place of Event: Washington, DC, USA
Start-/End Date: 2019-06-20 - 2019-06-25

Legal Case

show

Project information

show

Source 1

show
hide
Title: Annual Conference of the American Library Association (ALA 2019)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: 5 Start / End Page: 1 - 5 Identifier: -