Autobidding Arena: unified evaluation of the classical and RL-based autobidding algorithms

TL;DR

This paper introduces a standardized evaluation protocol for comparing classical and RL-based autobidding algorithms in online advertising, enabling fair, transparent, and reproducible benchmarking across different methods and platforms.

Contribution

It presents a unified benchmarking framework using industry-relevant environments to evaluate diverse autobidding algorithms with multiple metrics, highlighting their strengths and weaknesses.

Findings

RL-based autobidding algorithms show promising performance.

Classical algorithms excel in certain cost metrics.

The evaluation protocol improves comparability and reproducibility.

Abstract

Advertisement auctions play a crucial role in revenue generation for e-commerce companies. To make the bidding procedure scalable to thousands of auctions, the automatic bidding (autobidding) algorithms are actively developed in the industry. Therefore, the fair and reproducible evaluation of autobidding algorithms is an important problem. We present a standardized and transparent evaluation protocol for comparing classical and reinforcement learning (RL) autobidding algorithms. We consider the most efficient autobidding algorithms from different classes, e.g., ones based on the controllers, RL, optimal formulas, etc., and benchmark them in the bidding environment. We utilize the most recent open-source environment developed in the industry, which accurately emulates the bidding process. Our work demonstrates the most promising use cases for the considered autobidding algorithms, highlights their surprising drawbacks, and evaluates them according to multiple metrics. We select the evaluation metrics that illustrate the performance of the autobidding algorithms, the corresponding costs, and track the budget pacing. Such a choice of metrics makes our results applicable to the broad range of platforms where autobidding is effective. The presented comparison results help practitioners to evaluate the candidate autobidding algorithms from different perspectives and select ones that are efficient according to their companies' targets.