In multiagent systems (MASs), each agent makes individual decisions but all of them contribute globally to the system evolution. Learning in MASs is difficult since each agent's selection of actions must take place in the presence of other co-learning agents. Moreover, the environmental stochasticity and uncertainties increase exponentially with the increase in the number of agents. Previous works borrow various multiagent coordination mechanisms into deep learning architecture to facilitate multiagent coordination. However, none of them explicitly consider action semantics between agents that different actions have different influences on other agents. In this paper, we propose a novel network architecture, named Action Semantics Network (ASN), that explicitly represents such action semantics between agents. ASN characterizes different actions' influence on other agents using neural networks based on the action semantics between them. ASN can be easily combined with existing deep reinforcement learning (DRL) algorithms to boost their performance. Experimental results on StarCraft II micromanagement and Neural MMO show ASN significantly improves the performance of state-of-the-art DRL approaches compared with several network architectures.

中文翻译：

---

动作语义网络：考虑多智能体系统中动作的影响

在多智能体系统 (MAS) 中，每个智能体都做出单独的决策，但它们都对系统演化做出了全局性的贡献。在 MAS 中学习是困难的，因为每个智能体的动作选择必须在其他共同学习智能体存在的情况下进行。此外，环境随机性和不确定性随着代理数量的增加呈指数增长。以前的工作将各种多代理协调机制借用到深度学习架构中，以促进多代理协调。然而，他们都没有明确考虑代理之间的动作语义，即不同的动作对其他代理有不同的影响。在本文中，我们提出了一种新的网络架构，称为动作语义网络（ASN），它明确表示代理之间的这种动作语义。ASN 使用基于它们之间的动作语义的神经网络来表征不同动作对其他智能体的影响。ASN 可以轻松地与现有的深度强化学习 (DRL) 算法结合以提高其性能。星际争霸 II 微管理和神经 MMO 的实验结果表明，与几种网络架构相比，ASN 显着提高了最先进的 DRL 方法的性能。