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

10/23/2021
by   Tianqi Shen, et al.
0

Vital importance has necessity to be attached to cooperation in multi-agent environments, as a result of which some reinforcement learning algorithms combined with graph neural networks have been proposed to understand the mutual interplay between agents. However, highly complicated and dynamic multi-agent environments require more ingenious graph neural networks, which can comprehensively represent not only the graph topology structure but also evolution process of the structure due to agents emerging, disappearing and moving. To tackle these difficulties, we propose Gumbel Sinkhorn graph attention reinforcement learning, where a graph attention network highly represents the underlying graph topology structure of the multi-agent environment, and can adapt to the dynamic topology structure of graph better with the help of Gumbel Sinkhorn network by learning latent permutations. Empirically, simulation results show how our proposed graph reinforcement learning methodology outperforms existing methods in the PettingZoo multi-agent environment by learning latent permutations.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 8

research
04/08/2021

Learning to Coordinate via Multiple Graph Neural Networks

The collaboration between agents has gradually become an important topic...
research
08/20/2020

Multi-Agent Reinforcement Learning with Graph Clustering

In this paper, we introduce the group concept into multi-agent reinforce...
research
02/11/2020

Learning Structured Communication for Multi-agent Reinforcement Learning

This work explores the large-scale multi-agent communication mechanism u...
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
03/23/2023

Stochastic Graph Neural Network-based Value Decomposition for MARL in Internet of Vehicles

Autonomous driving has witnessed incredible advances in the past several...
research
10/22/2018

Graph Convolutional Reinforcement Learning for Multi-Agent Cooperation

Learning to cooperate is crucially important in multi-agent reinforcemen...
research
01/20/2023

Multi-agent Reinforcement Learning with Graph Q-Networks for Antenna Tuning

Future generations of mobile networks are expected to contain more and m...

Please sign up or login with your details

Forgot password? Click here to reset