Golden
Geek.AI MAgent

Geek.AI MAgent

a platform to support research and development of many-agent reinforcement learning.

All edits

Edits on 13 Apr 2019
Jessica Karpinski
Jessica Karpinski edited on 13 Apr 2019 8:15 pm
Edits made to:
Infobox (+2 properties)
Edits on 24 Feb 2019
Daniel Frumkin
Daniel Frumkin approved a suggestion from Golden's AI on 24 Feb 2019 4:04 pm
Edits made to:
Article (+5/-5 characters)

Article

MAgent supports LinuxLinux and OS X running Python 2.7 or python 3 and is compatible with rule-based algorithms and deep learning frameworks.

Daniel Frumkin"Added related topics"
Daniel Frumkin edited on 24 Feb 2019 4:03 pm
Edits made to:
Related Topics (+3/-1 topics)
Daniel Frumkin"Created page"
Daniel Frumkin edited on 24 Feb 2019 4:02 pm
Edits made to:
Infobox (+3 properties)
Description (+84 characters)
Article (+1 videos) (+1284 characters)
People (+12 cells) (+103 characters)
Further reading (+8 cells) (+334 characters)
Documentaries, videos and podcasts (+3 cells) (+144 characters)
Categories (+1 topics)
Related Topics (+4 topics)
Topic thumbnail

Geek.AI MAgent

a platform to support research and development of many-agent reinforcement learning.

Article

Geek.AI MAgent is a research platform for many-agent reinforcement learning (MARL). Unlike previous research platforms that focus on reinforcement learning research with a single agent or only few agents, MAgent aims at supporting reinforcement learning research that scales up from hundreds to millions of agents.



MAgent is able to host up to one million agents on a single GPU server. It provides environment/agent configurations and a reward description language to enable flexible environment design. Through this platform, Geek.AI has been able to demonstrate emerged collective intelligence by learning from scratch.





MAgent supports Linux and OS X running Python 2.7 or python 3 and is compatible with rule-based algorithms and deep learning frameworks.

About Geek.AI

Geek.AI is a joint research team the UK and China, with representatives from Shanghai Jiao Tong Unviersity and University College London. They are dedicated to fundamental research topics of multi-agent reinforcement learning and its potential for real-world applications through AI coordination, learning to communicate, reinforcement learning with massive numbers of agents, self-play, learning to design multi-agent environments, personality learning for AI agents, GANs for discrete data generation, and more.

People

Name
Role
Related Golden topics

Han Cai

Creator



Jiacheng Yang

Creator



Jun Wang

Creator



Lianmin Zheng

Creator



Weinan Zhang

Creator



Yong Yu

Creator



Further reading

Title
Author
Link
Type

Cases for Applying Multi-Agent Reinforcement Learning -- Silo.AI

Zhen Li

Web

MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence

Lianmin Zheng, Jiacheng Yang, Han Cai, Weinan Zhang, Jun Wang, Yong Yu

PDF

Documentaries, videos and podcasts

Title
Date
Link

A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence

September 18, 2017

Infobox

Categories

Related Topics

Daniel Frumkin"Initial topic creation"
Daniel Frumkin created this topic on 24 Feb 2019 3:37 pm
Edits made to:
Topic thumbnail

 Geek.AI MAgent

a platform to support research and development of many-agent reinforcement learning.

No more activity to show.