KnowSR: Knowledge Sharing among Homogeneous Agents in Multi-agent Reinforcement Learning
This addresses training efficiency for multi-agent systems, offering an incremental improvement by adapting existing MARL algorithms with knowledge distillation.
The paper tackles the resource-intensive training of multi-agent reinforcement learning by proposing KnowSR, a knowledge sharing method among homogeneous agents, which shortens training time and outperforms recent methodologies in collaborative and competitive scenarios.
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.