# Comparative Evaluation of Multiagent Learning Algorithms in a Diverse Set of Ad Hoc Team Problems

## TL;DR

This paper empirically evaluates five multiagent learning algorithms in diverse ad hoc team problems where agents are heterogeneous and adapt their behaviors, revealing no clear overall best but highlighting different strengths.

## Contribution

It provides a comparative analysis of major multiagent learning algorithms in heterogeneous, adaptive ad hoc team settings, which is less explored in prior work.

## Key findings

- No single algorithm outperforms others across all criteria.
- Different algorithms excel in specific performance aspects like social welfare or equilibrium attainment.
- Heterogeneous, adaptive agents pose unique challenges for multiagent learning algorithms.

## Abstract

This paper is concerned with evaluating different multiagent learning (MAL) algorithms in problems where individual agents may be heterogenous, in the sense of utilizing different learning strategies, without the opportunity for prior agreements or information regarding coordination. Such a situation arises in ad hoc team problems, a model of many practical multiagent systems applications. Prior work in multiagent learning has often been focussed on homogeneous groups of agents, meaning that all agents were identical and a priori aware of this fact. Also, those algorithms that are specifically designed for ad hoc team problems are typically evaluated in teams of agents with fixed behaviours, as opposed to agents which are adapting their behaviours. In this work, we empirically evaluate five MAL algorithms, representing major approaches to multiagent learning but originally developed with the homogeneous setting in mind, to understand their behaviour in a set of ad hoc team problems. All teams consist of agents which are continuously adapting their behaviours. The algorithms are evaluated with respect to a comprehensive characterisation of repeated matrix games, using performance criteria that include considerations such as attainment of equilibrium, social welfare and fairness. Our main conclusion is that there is no clear winner. However, the comparative evaluation also highlights the relative strengths of different algorithms with respect to the type of performance criteria, e.g., social welfare vs. attainment of equilibrium.