The Composite Task Challenge for Cooperative Multi-Agent Reinforcement Learning

TL;DR

This paper introduces a new set of cooperative multi-agent reinforcement learning tasks that require division of labor, aiming to better evaluate and develop MARL methods for real-world applications.

Contribution

The authors designed and validated a series of tasks emphasizing division of labor, filling a gap in existing testbeds and promoting more realistic MARL research.

Findings

Baseline methods perform poorly on new tasks

Simplified task variants are solvable by existing methods

Proposed tasks demand division of labor for success

Abstract

The significant role of division of labor (DOL) in promoting cooperation is widely recognized in real-world applications.Many cooperative multi-agent reinforcement learning (MARL) methods have incorporated the concept of DOL to improve cooperation among agents.However, the tasks used in existing testbeds typically correspond to tasks where DOL is often not a necessary feature for achieving optimal policies.Additionally, the full utilize of DOL concept in MARL methods remains unrealized due to the absence of appropriate tasks.To enhance the generality and applicability of MARL methods in real-world scenarios, there is a necessary to develop tasks that demand multi-agent DOL and cooperation.In this paper, we propose a series of tasks designed to meet these requirements, drawing on real-world rules as the guidance for their design.We guarantee that DOL and cooperation are necessary condition for completing tasks and introduce three factors to expand the diversity of proposed tasks to cover more realistic situations.We evaluate 10 cooperative MARL methods on the proposed tasks.The results indicate that all baselines perform poorly on these tasks.To further validate the solvability of these tasks, we also propose simplified variants of proposed tasks.Experimental results show that baselines are able to handle these simplified variants, providing evidence of the solvability of the proposed tasks.The source files is available at https://github.com/Yurui-Li/CTC.