VIDEO DOI: https://doi.org/10.48448/a3v1-h738
PAPER DOI: Mean Field Methods; Multiagent Systems; Reinforcement Learning; Many Agent Learning

technical paper

AAMAS 2020

May 11, 2020

Live on Underline

Multi Type Mean Field Reinforcement Learning

Mean field theory provides an effective way of scaling multiagent reinforcement learning algorithms to environments with many agents that can be abstracted by a virtual mean agent. In this paper, we extend mean field multiagent algorithms to multiple types. The types enable the relaxation of a core assumption in mean field games, which is that all agents in the environment are playing almost similar strategies and have the same goal. We conduct experiments on three different testbeds for the field of many agent reinforcement learning, based on the standard MAgents framework. We consider two different kinds of mean field games: a) Games where agents belong to predefined types that are known a priori and b) Games where the type of each agent is unknown and therefore must be learned based on observations. We introduce new algorithms for each type of game and demonstrate their superior performance over state of the art algorithms that assume that all agents belong to the same type and other baseline algorithms in the MAgent framework.

Downloads

SlidesTranscript English (automatic)

Next from AAMAS 2020

technical paper

Gifting in Multi-Agent Reinforcement Learning

AAMAS 2020

Andrei Lupu and 1 other author

11 May 2020

Similar lecture

poster

DeAR: A Deep-learning-based Audio Re-recording Resilient Watermarking

AAAI 2023

+3
chang liu and 5 other authors

10 February 2023

Stay up to date with the latest Underline news!

PRESENTATIONS

  • All Lectures
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2023 Underline - All rights reserved