Heterogeneous Multi-Agent Task-Assignment with Uncertain Execution Times and Preferences

2025-10-17

AI Summary

This paper addresses the periodic task allocation problem in heterogeneous multi-agent systems, where agents possess diverse capabilities and task preferences, and task execution times, resource consumptions, and rewards follow unknown distributions. A central planner must dynamically assign recurring tasks within a finite time horizon to maximize the team’s expected cumulative reward while respecting individual agent resource constraints. To tackle dual uncertainties—agent capability and preference—we formulate the problem as a stochastic multi-armed bandit framework, integrating linear programming with confidence-bound optimization, and propose a novel online learning algorithm. We theoretically establish an $O(sqrt{T})$ upper bound on its cumulative regret. Empirical evaluations demonstrate that our approach significantly outperforms baseline strategies across diverse uncertainty settings, achieving both high allocation efficiency and solution stability.

Technology Category

• Multiagent Systems: Mechanism Design
• Machine Learning: Online Learning & Bandits
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

While sequential task assignment for a single agent has been widely studied, such problems in a multi-agent setting, where the agents have heterogeneous task preferences or capabilities, remain less well-characterized. We study a multi-agent task assignment problem where a central planner assigns recurring tasks to multiple members of a team over a finite time horizon. For any given task, the members have heterogeneous capabilities in terms of task completion times, task resource consumption (which can model variables such as energy or attention), and preferences in terms of the rewards they collect upon task completion. We assume that the reward, execution time, and resource consumption for each member to complete any task are stochastic with unknown distributions. The goal of the planner is to maximize the total expected reward that the team receives over the problem horizon while ensuring that the resource consumption required for any assigned task is within the capability of the agent. We propose and analyze a bandit algorithm for this problem. Since the bandit algorithm relies on solving an optimal task assignment problem repeatedly, we analyze the achievable regret in two cases: when we can solve the optimal task assignment exactly and when we can solve it only approximately.

Problem

• Assigning heterogeneous agents to recurring tasks with uncertain parameters
• Maximizing team rewards while respecting individual resource constraints
• Developing bandit algorithms for stochastic multi-agent task assignment

Innovation

• Bandit algorithm for multi-agent task assignment
• Handles stochastic rewards and resource constraints
• Analyzes regret for exact and approximate solutions