社会行为作为基于学习的多智能体路径规划困境的关键
Social Behavior as a Key to Learning-based Multi-Agent Pathfinding Dilemmas
AI总结：
本文提出 SYLPH 框架，通过让共享参数的 MAPF 智能体动态选择社会价值取向并交换社会偏好，缓解同质化行为导致的死锁与活锁问题，从而提升对称冲突下的路径规划能力。
摘要：
多智能体路径规划（Multi-agent Path Finding, MAPF）问题涉及在已知、静态环境中为一组智能体寻找无碰撞路径，在仓库自动化、物流或末端配送中具有重要应用。为了满足这些大规模应用的需求，当前基于学习的方法通常将同一个完全训练好的去中心化网络部署到所有智能体上，以提高可扩展性。然而，这种参数共享通常会导致智能体之间行为同质化，这可能使智能体无法在对称冲突（例如瓶颈）中打破僵局，并可能导致活锁或死锁。在本文中，我们提出 SYLPH，一种新颖的基于学习的 MAPF 框架，旨在通过允许智能体学习并动态选择不同的社会行为（类似于个体化、动态的角色）来缓解同质化的不利影响，同时不影响参数共享所提供的可扩展性。具体而言，SYLPH 智能体学习根据当前情境选择其社会价值取向（Social Value Orientation, SVO），量化其自身的自私/利他程度，并学习一个以 SVO 为条件的 MAPF 策略来决定其移动动作。为此，每个智能体首先通过预测与其他智能体未来的冲突/交互来确定系统中对其影响最大的其他智能体。每个智能体针对该智能体选择自己的 SVO，并训练其去中心化 MAPF 策略以执行该 SVO，直到另一个智能体变得更具影响力。为了进一步让智能体考虑彼此的社会偏好，每个智能体可以获取其邻居的 SVO 值。由于这种分层决策和社会偏好的交换，SYLPH 赋予智能体通过更多潜在空间和细致语境来推理 MAPF 任务的能力，从而产生多样化的响应，有助于打破对称冲突中的僵局。
英文摘要：
The Multi-agent Path Finding (MAPF) problem involves finding collision-free paths for a team of agents in a known, static environment, with important applications in warehouse automation, logistics, or last-mile delivery. To meet the needs of these large-scale applications, current learning-based methods often deploy the same fully trained, decentralized network to all agents to improve scalability. However, such parameter sharing typically results in homogeneous behaviors among agents, which may prevent agents from breaking ties around symmetric conflict (e.g., bottlenecks) and might lead to live-/deadlocks. In this paper, we propose SYLPH, a novel learning-based MAPF framework aimed to mitigate the adverse effects of homogeneity by allowing agents to learn and dynamically select different social behaviors (akin to individual, dynamic roles), without affecting the scalability offered by parameter sharing. Specifically, SYLPH agents learn to select their Social Value Orientation (SVO) given the situation at hand, quantifying their own level of selfishness/altruism, as well as an SVO-conditioned MAPF policy dictating their movement actions. To these ends, each agent first determines the most influential other agent in the system by predicting future conflicts/interactions with other agents. Each agent selects its own SVO towards that agent, and trains its decentralized MAPF policy to enact this SVO until another agent becomes more influential. To further allow agents to consider each others' social preferences, each agent gets access to the SVO value of their neighbors. As a result of this hierarchical decision-making and exchange of social preferences, SYLPH endows agents with the ability to reason about the MAPF task through more latent spaces and nuanced contexts, leading to varied responses that can help break ties around symmetric conflicts. [...]
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。
