KnowSR: Knowledge Sharing among Homogeneous Agents in Multi-agent Reinforcement Learning

TL;DR

KnowSR introduces a knowledge sharing method for homogeneous multi-agent reinforcement learning that accelerates training and improves performance by leveraging knowledge distillation among agents.

Contribution

The paper proposes KnowSR, a novel knowledge sharing approach using knowledge distillation to enhance homogeneous multi-agent RL training efficiency.

Findings

KnowSR accelerates training in multi-agent RL scenarios.

KnowSR outperforms existing methods in collaborative and competitive tasks.

Knowledge sharing improves robustness and effectiveness of MARL algorithms.

Abstract

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.