Graph Convolutional Reinforcement Learning for Multi-Agent Cooperation

10/22/2018
by   Jiechuan Jiang, et al.
0

Learning to cooperate is crucially important in multi-agent reinforcement learning. The key is to take the influence of other agents into consideration when performing distributed decision making. However, multi-agent environment is highly dynamic, which makes it hard to learn abstract representations of influences between agents by only low-order features that existing methods exploit. In this paper, we propose a graph convolutional model for multi-agent cooperation. The graph convolution architecture adapts to the dynamics of the underlying graph of the multi-agent environment, where the influence among agents is captured by their abstract relation representations. High-order features extracted by relation kernels of convolutional layers from gradually increased receptive fields are exploited to learn cooperative strategies. The gradient of an agent not only backpropagates to itself but also to other agents in its receptive fields to reinforce the learned cooperative strategies. Moreover, the relation representations are temporally regularized to make the cooperation more consistent. Empirically, we show that our model enables agents to develop more cooperative and sophisticated strategies than existing methods in jungle and battle games and routing in packet switching networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/20/2018

Learning Attentional Communication for Multi-Agent Cooperation

Communication could potentially be an effective way for multi-agent coop...
research
10/23/2021

Foresight of Graph Reinforcement Learning Latent Permutations Learnt by Gumbel Sinkhorn Network

Vital importance has necessity to be attached to cooperation in multi-ag...
research
05/24/2022

Graph Convolutional Reinforcement Learning for Collaborative Queuing Agents

In this paper, we explore the use of multi-agent deep learning as well a...
research
12/07/2022

Distributed Interaction Graph Construction for Dynamic DCOPs in Cooperative Multi-agent Systems

DCOP algorithms usually rely on interaction graphs to operate. In open a...
research
10/17/2019

MAPEL: Multi-Agent Pursuer-Evader Learning using Situation Report

In this paper, we consider a territory guarding game involving pursuers,...
research
12/01/2020

Gaussian Process Based Message Filtering for Robust Multi-Agent Cooperation in the Presence of Adversarial Communication

In this paper, we consider the problem of providing robustness to advers...
research
11/29/2021

Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning

Safety is the primary concern when it comes to air traffic. In-flight sa...

Please sign up or login with your details

Forgot password? Click here to reset