Solving Multi-Agent Sokoban via LaCAM
Keisuke Okumura
Abstract
Sokoban, a puzzle game in which an agent pushes boxes onto unlabelled target locations in a grid world, is a long-standing benchmark planning problem. While it is easy to see the connection to practical applications such as warehouse logistics with autonomous forklifts, its multi-agent counterpart has remained underdeveloped. This is because Multi-Agent Sokoban is substantially more difficult due to factors specific to multi-agent planning, such as the rapidly growing branching factor as the number of agents grows and the need to handle integrated task assignment and collision-free pathfinding. In this paper, we show that a scalable planner for Multi-Agent Sokoban can be designed by leveraging recent advances in multi-agent pathfinding (MAPF). Specifically, our Sokoban-LaCAM efficiently solves instances involving tens of agents and boxes while preserving both completeness and eventual optimality guarantees. This provides evidence that MAPF can serve as a powerful primitive for solving broader collective automation problems.
Create a lesson
Related papers
After Cooperation Is Learned: Gradient Routing and Optimizer-Dependent Maintenance in Multi-Agent Reinforcement Learning
Chaoyuan Hao, Wentao Yue, Tianyou Lai et al.
Managing Context and Communication in Distributed Agentic UAV Swarms
Andrea Iannoli, Ivan Zyrianoff, Angelo Trotta et al.
LLM-Driven Multi-Agent Control for Skill-Based Smart Manufacturing
Kay Köhle, Darko Anicic, Thomas A. Runkler et al.
Can AI Scientists Coordinate at Runtime?
Zijian Liu, Yangzhixin Luo, Junyu Lu et al.
Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
Yunbei Zhang, Saiyue Lyu, Janet Wang et al.
Consensus and Factual Dynamics in Large Populations of Interacting Language Models
Emanuele Ricco, Elia Onofri, Vincenzo Sammartino et al.