Single-Agent Planning in a Multi-Agent System: A Unified Framework for Type-Based Planners

TL;DR

This paper introduces a unified theoretical framework for single-agent planning in multi-agent environments, balancing exploration and exploitation, and evaluates 13 planners in multi-agent route planning with up to 50 agents.

Contribution

It presents a novel unified framework that encompasses various planning strategies for a single agent in multi-agent settings, including exact and approximate solutions.

Findings

Safe-agent planners perform well across scenarios.

Enhanced domain-specific planners improve efficiency.

Framework offers new insights into multi-agent decision-making.

Abstract

We consider a general problem where an agent is in a multi-agent environment and must plan for herself without any prior information about her opponents. At each moment, this pivotal agent is faced with a trade-off between exploiting her currently accumulated information about the other agents and exploring further to improve future (re-)planning. We propose a theoretic framework that unifies a spectrum of planners for the pivotal agent to address this trade-off. The planner at one end of this spectrum aims to find exact solutions, while those towards the other end yield approximate solutions as the problem scales up. Beyond theoretical analysis, we also implement \textbf{13} planners and conduct experiments in a specific domain called \textit{multi-agent route planning} with the number of agents \textbf{up to~50}, to compare their performaces in various scenarios. One interesting observation comes from a class of planners that we call \textit{safe-agents} and their enhanced variants by incorporating domain-specific knowledge, which is a simple special case under the proposed general framework, but performs sufficiently well in most cases. Our unified framework, as well as those induced planners, provides new insights on multi-agent decision-making, with potential applications to related areas such as mechanism design.