Recently, deep reinforcement learning (RL) algorithms have made great progress in multi-agent domain. However, due to characteristics of RL, training for complex tasks would be resource-intensive and time-consuming. To meet this challenge, mutual learning strategy between homogeneous agents is essential, which is under-explored in previous studies, because most existing methods do not consider to use the knowledge of agent models. In this paper, we present an adaptation method of the majority of multi-agent reinforcement learning (MARL) algorithms called KnowSR which takes advantage of the differences in learning between agents. We employ the idea of knowledge distillation (KD) to share knowledge among agents to shorten the training phase. To empirically demonstrate the robustness and effectiveness of KnowSR, we performed extensive experiments on state-of-the-art MARL algorithms in collaborative and competitive scenarios. The results demonstrate that KnowSR outperforms recently reported methodologies, emphasizing the importance of the proposed knowledge sharing for MARL.

翻译：最近,深入强化学习(RL)算法在多试剂领域取得了巨大进展,然而,由于RL的特点,复杂任务的培训将耗费大量资源和时间。为了迎接这一挑战,同质代理商之间的相互学习战略至关重要,以往的研究对此探索不足,因为大多数现有方法不考虑使用代理商模型的知识。在本文件中,我们介绍了大多数多试剂强化学习(MARL)算法的适应方法,称为“KnowSR”,它利用了代理商之间学习差异的优势。我们利用知识蒸馏(KD)的想法在代理商之间分享知识以缩短培训阶段。为了从经验上证明KnowSR的稳健性和有效性,我们在协作和竞争的情景中就最先进的MARL算法进行了广泛的实验。结果显示,KnowSR超越了最近报告的方法,强调了拟议的MARL知识共享的重要性。