基于采样的协调感知多目标多机器人强化学习
Sampling-Based Coordination-Informed Multi-Objective Multi-Robot Reinforcement Learning
AI总结：
提出CIMORL框架，通过分布式权重预测、特权专家训练和采样变体（CIMORL-TS/MPPI），在合作与对抗场景中实现Pareto最优解，超体积提升21.2%。
摘要：
多机器人系统必须同时优化竞争目标并保持协调行为。现有的多智能体强化学习方法通常依赖固定或集中式协调，这限制了适应性并违反了分布式约束。本文引入了协调感知多目标强化学习（CIMORL）框架，集成了分布式权重预测机制、特权专家训练策略以及Pareto最优解的理论保证。我们提出了基础CIMORL方法以及两种基于采样的变体，CIMORL-TS（树搜索）和CIMORL-MPPI（MPPI），它们在训练期间利用特权全局信息以实现完全分散的部署。在合作和对抗场景中的实验验证表明，与最先进的基线相比，超体积改进达21.2%，且策略稳定性更优。使用Crazyflie无人机进行的真实世界实验进一步验证了该框架在部分可观测条件下资源分配和多攻击者多防御场景中的鲁棒性。
英文摘要：
Multi-robot systems must simultaneously optimize competing objectives while maintaining coordinated behavior. Existing multi-agent reinforcement learning approaches often rely on fixed or centralized coordination, which limits adaptability and violates distributed constraints. This work introduces the Coordination-Informed Multi-Objective Reinforcement Learning (CIMORL) framework, integrating a distributed weight prediction mechanism, a privileged expert training strategy, and theoretical guarantees for Pareto-optimal solutions. We present the base CIMORL method alongside two sampling-based variants, CIMORL-TS (Tree Search) and CIMORL-MPPI (MPPI), which leverage privileged global information during training to enable fully decentralized deployment. Experimental validation in cooperative and adversarial scenarios demonstrates a $21.2\%$ hypervolume improvement and superior policy stability compared to state-of-the-art baselines. Real-world experiments with Crazyflie drones further validate the framework's robustness in resource allocation and multi-attacker multi-defend scenarios under partial observability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
