Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learning
arXiv:2010.04740
Abstract
We propose a novel framework for value function factorization in multi-agent deep reinforcement learning (MARL) using graph neural networks (GNNs). In particular, we consider the team of agents as the set of nodes of a complete directed graph, whose edge weights are governed by an attention mechanism. Building upon this underlying graph, we introduce a mixing GNN module, which is responsible for i) factorizing the team state-action value function into individual per-agent observation-action value functions, and ii) explicit credit assignment to each agent in terms of fractions of the global team reward. Our approach, which we call GraphMIX, follows the centralized training and decentralized execution paradigm, enabling the agents to make their decisions independently once training is completed. We show the superiority of GraphMIX as compared to the state-of-the-art on several scenarios in the StarCraft II multi-agent challenge (SMAC) benchmark. We further demonstrate how GraphMIX can be used in conjunction with a recent hierarchical MARL architecture to both improve the agents' performance and enable fine-tuning them on mismatched test scenarios with higher numbers of agents and/or actions.
References in corpus (12)
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Counterfactual Multi-Agent Policy Gradients
- Emergent Tool Use From Multi-Agent Autocurricula
- Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks
- Attention-based Graph Neural Network for Semi-supervised Learning
- QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning
- Strategies for Pre-training Graph Neural Networks
- QPLEX: Duplex Dueling Multi-Agent Q-Learning
- Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
- RODE: Learning Roles to Decompose Multi-Agent Tasks
- Multi-agent Reinforcement Learning for Networked System Control
- Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning