# On the Robustness of Epoch-Greedy in Multi-Agent Contextual Bandit Mechanisms

arXiv: https://arxiv.org/abs/2307.07675 · HTML: https://mlsanity.com/paper/2307.07675/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 24 references that are in the map.
- First posted on arXiv 15 Jul 2023.

## Builds on (most cited first, 5 of 5)

- [Stochastic bandits robust to adversarial corruptions](https://mlsanity.com/paper/1803.09353/) (2018)
- [Better Algorithms for Stochastic Bandits with Adversarial Corruptions](https://mlsanity.com/paper/1902.08647/) (2019)
- [Learning Prices for Repeated Auctions with Strategic Buyers](https://mlsanity.com/paper/1311.6838/) (2013)
- [Multi-armed Bandit Problems with Strategic Arms](https://mlsanity.com/paper/1706.09060/) (2017)
- [Learning Optimal Reserve Price against Non-myopic Bidders](https://mlsanity.com/paper/1804.11060/) (2018)

## Built on by (most cited first, 3 of 3)

- [Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation](https://mlsanity.com/paper/2311.15647/) (2023)
- [Online Learning in Contextual Second-Price Pay-Per-Click Auctions](https://mlsanity.com/paper/2310.05047/) (2023)
- [Robust Thompson Sampling Algorithms Against Reward Poisoning Attacks](https://mlsanity.com/paper/2410.19705/) (2024)

## Abstract (arXiv)

Efficient learning in multi-armed bandit mechanisms such as pay-per-click (PPC) auctions typically involves three challenges: 1) inducing truthful bidding behavior (incentives), 2) using personalization in the users (context), and 3) circumventing manipulations in click patterns (corruptions). Each of these challenges has been studied orthogonally in the literature; incentives have been addressed by a line of work on truthful multi-armed bandit mechanisms, context has been extensively tackled by contextual bandit algorithms, while corruptions have been discussed via a recent line of work on bandits with adversarial corruptions. Since these challenges co-exist, it is important to understand the robustness of each of these approaches in addressing the other challenges, provide algorithms that can handle all simultaneously, and highlight inherent limitations in this combination. In this work, we show that the most prominent contextual bandit algorithm, ε-greedy can be extended to handle the challenges introduced by strategic arms in the contextual multi-arm bandit mechanism setting. We further show that ε-greedy is inherently robust to adversarial data corruption attacks and achieves performance that degrades linearly with the amount of corruption.