Value Function Factorisation with Hypergraph Convolution for Cooperative Multi-agent Reinforcement Learning

12/09/2021
by   Yunpeng Bai, et al.
0

Cooperation between agents in a multi-agent system (MAS) has become a hot topic in recent years, and many algorithms based on centralized training with decentralized execution (CTDE), such as VDN and QMIX, have been proposed. However, these methods disregard the information hidden in the individual action values. In this paper, we propose HyperGraph CoNvolution MIX (HGCN-MIX), a method that combines hypergraph convolution with value decomposition. By treating action values as signals, HGCN-MIX aims to explore the relationship between these signals via a self-learning hypergraph. Experimental results present that HGCN-MIX matches or surpasses state-of-the-art techniques in the StarCraft II multi-agent challenge (SMAC) benchmark on various situations, notably those with a number of agents.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/22/2020

QOPT: Optimistic Value Function Decentralization for Cooperative Multi-Agent Reinforcement Learning

We propose a novel value-based algorithm for cooperative multi-agent rei...
research
03/07/2022

Efficient Cooperation Strategy Generation in Multi-Agent Video Games via Hypergraph Neural Network

The performance of deep reinforcement learning (DRL) in single-agent vid...
research
05/30/2022

Residual Q-Networks for Value Function Factorizing in Multi-Agent Reinforcement Learning

Multi-Agent Reinforcement Learning (MARL) is useful in many problems tha...
research
03/28/2022

UNMAS: Multi-Agent Reinforcement Learning for Unshaped Cooperative Scenarios

Multi-agent reinforcement learning methods such as VDN, QMIX, and QTRAN ...
research
12/22/2020

QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning

This paper introduces four new algorithms that can be used for tackling ...
research
01/04/2023

Attention-Based Recurrence for Multi-Agent Reinforcement Learning under State Uncertainty

State uncertainty poses a major challenge for decentralized coordination...
research
10/28/2020

Learning to Represent Action Values as a Hypergraph on the Action Vertices

Action-value estimation is a critical component of many reinforcement le...

Please sign up or login with your details

Forgot password? Click here to reset