提出无通信框架SPI，解决多智能体推箱时相互抵消力的问题。
Efficient Training in Multi-Agent Reinforcement Learning: A Communication-Free Framework for the Box-Pushing Problem
- 引入共享信息池让所有智能体同步感知环境，无需直接通信
- 训练速度提升，单轮步数减少约40%（对比基线）
- 适合需要高效协作的分布式任务场景
自组织系统由自主智能体组成，可在无中央控制器的情况下完成复杂任务并适应动态环境。以往研究常采用强化学习使智能体掌握任务技能，如在推箱环境中。然而，在探索过程中，若智能体从相反方向推动箱子，会产生大小相等、方向相反的力，导致箱子几乎不动，训练效率低下。本文提出一种名为共享信息池（Shared Pool of Information, SPI）的模型，使所有智能体可访问统一信息源，促进协调，减少力量冲突，提升探索效率。通过计算机模拟验证，SPI不仅显著加速训练过程，且每回合所需步数减少约40%，大幅提高智能体协同能力。
原文摘要 · Abstract (English)
Self-organizing systems consist of autonomous agents that can perform complex tasks and adapt to dynamic environments without a central controller. Prior research often relies on reinforcement learning to enable agents to gain the skills needed for task completion, such as in the box-pushing environment. However, when agents push from opposing directions during exploration, they tend to exert equal and opposite forces on the box, resulting in minimal displacement and inefficient training. This paper proposes a model called Shared Pool of Information (SPI), which enables information to be accessible to all agents and facilitates coordination, reducing force conflicts among agents and enhancing exploration efficiency. Through computer simulations, we demonstrate that SPI not only expedites the training process but also requires fewer steps per episode, significantly improving the agents' collaborative effectiveness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。