用模块化方法让群体机器人高效协作，降低记忆负担。
Modular Reinforcement Learning For Cooperative Swarms
- 将交互状态分解为独立模块学习，避免组合爆炸
- 在仿真觅食任务中实现稳定协作，性能优于传统方法
- 适合资源受限的分布式机器人系统，如微型无人机群
协作式机器人集群是由计算能力有限的机器人组成的集体，它们共享共同目标，但每台机器人只能与少数同伴交互，且无法知晓这种交互如何影响整体效用。近年来分布式多智能体强化学习的进步表明，即使各机器人独立学习，也能学会有效互动以达成共同目标。然而，这要求每个机器人需表示可能呈组合爆炸的交互状态，超出其内存承载能力。本文提出一种用于群体机器人强化学习的空间交互状态新表示方法：采用模块化（分解式）结构，每个状态特征由独立的学习过程处理，结果再聚合。我们在多个模拟机器人集群的觅食实验中验证了该方法的有效性。
原文摘要 · Abstract (English)
A cooperative robot swarm is a collective of computationally-limited robots that share a common goal. Each robot can only interact with a small subset of its peers, without knowing how this affects the collective utility. Recent advances in distributed multi-agent reinforcement learning have demonstrated that it is possible for robots to learn how to interact effectively with others, in a manner that is aligned with the common goal, despite each robot learning independently of others. However, this requires each robot to represent a potentially combinatorial number of interaction states, challenging the memory capabilities of the robots. This paper proposes an alternative approach for representing spatial interaction states for multi-robot reinforcement learning in swarms. A modular (decomposed) representation is used, where each feature of the state is handled by a separate learning procedure, and the results aggregated. We demonstrate the efficacy of the approach in numerous experiments with simulated robot swarms carrying out foraging.
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。