Learning Transferable Cooperative Behavior in Multi-Agent Teams

06/04/2019
by   Akshat Agarwal, et al.
0

While multi-agent interactions can be naturally modeled as a graph, the environment has traditionally been considered as a black box. We propose to create a shared agent-entity graph, where agents and environmental entities form vertices, and edges exist between the vertices which can communicate with each other. Agents learn to cooperate by exchanging messages along the edges of this graph. Our proposed multi-agent reinforcement learning framework is invariant to the number of agents or entities present in the system as well as permutation invariance, both of which are desirable properties for any multi-agent system representation. We present state-of-the-art results on coverage, formation and line control tasks for multi-agent teams in a fully decentralized framework and further show that the learned policies quickly transfer to scenarios with different team sizes along with strong zero-shot generalization performance. This is an important step towards developing multi-agent teams which can be realistically deployed in the real world without assuming complete prior knowledge or instantaneous communication at unbounded distances.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/06/2020

Heterogeneous Multi-Agent Reinforcement Learning for Unknown Environment Mapping

Reinforcement learning in heterogeneous multi-agent scenarios is importa...
research
09/28/2018

Relational Forward Models for Multi-Agent Learning

The behavioral dynamics of multi-agent systems have a rich and orderly s...
research
06/07/2020

AI-QMIX: Attention and Imagination for Dynamic Multi-Agent Reinforcement Learning

Real world multi-agent tasks often involve varying types and quantities ...
research
10/10/2021

Cooperative Assistance in Robotic Surgery through Multi-Agent Reinforcement Learning

Cognitive cooperative assistance in robot-assisted surgery holds the pot...
research
09/28/2020

Towards Heterogeneous Multi-Agent Reinforcement Learning with Graph Neural Networks

This work proposes a neural network architecture that learns policies fo...
research
01/13/2023

TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems

Coordination is one of the most difficult aspects of multi-agent reinfor...
research
09/20/2022

LEMURS: Learning Distributed Multi-Robot Interactions

This paper presents LEMURS, an algorithm for learning scalable multi-rob...

Please sign up or login with your details

Forgot password? Click here to reset