论文标题
使用图神经网络进行异质的多机构增强学习
Towards Heterogeneous Multi-Agent Reinforcement Learning with Graph Neural Networks
论文作者
论文摘要
这项工作提出了一种神经网络体系结构，该架构在异质的多代理增强设置中学习多个代理类的政策。所提出的网络使用定向标记的图表表示状态，编码不同大小的不同实体类别的向量，使用关系图卷积层在实体类型之间建模不同的通信通道，并了解不同代理类别的不同策略，并在可能的情况下共享参数。结果表明，在实体类之间专门研究沟通渠道是在由异质实体组成的环境中实现更高绩效的有希望的步骤。
This work proposes a neural network architecture that learns policies for multiple agent classes in a heterogeneous multi-agent reinforcement setting. The proposed network uses directed labeled graph representations for states, encodes feature vectors of different sizes for different entity classes, uses relational graph convolution layers to model different communication channels between entity types and learns distinct policies for different agent classes, sharing parameters wherever possible. Results have shown that specializing the communication channels between entity classes is a promising step to achieve higher performance in environments composed of heterogeneous entities.
