# Multi-Agent Bandit Learning through Heterogeneous Action Erasure Channels

arXiv: https://arxiv.org/abs/2312.14259 · HTML: https://mlsanity.com/paper/2312.14259/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 37 references that are in the map.
- First posted on arXiv 21 Dec 2023.

## Builds on (most cited first, 10 of 10)

- [Online Learning under Delayed Feedback](https://mlsanity.com/paper/1306.0686/) (2013)
- [Stochastic Bandit Models for Delayed Conversions](https://mlsanity.com/paper/1706.09186/) (2017)
- [Cooperative Multi-Agent Bandits with Heavy Tails](https://mlsanity.com/paper/2008.06244/) (2020)
- [Best arm identification in multi-armed bandits with delayed feedback](https://mlsanity.com/paper/1803.10937/) (2018)
- [Multi-Agent Multi-Armed Bandits with Limited Communication](https://mlsanity.com/paper/2102.08462/) (2021)
- [Prediction with Corrupted Expert Advice](https://mlsanity.com/paper/2002.10286/) (2020)
- [Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization](https://mlsanity.com/paper/2110.14622/) (2021)
- [Solving Multi-Arm Bandit Using a Few Bits of Communication](https://mlsanity.com/paper/2111.06067/) (2021)
- [Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards](https://mlsanity.com/paper/2306.05579/) (2023)
- [Forwarding, Caching and Congestion Control in Named Data Networks](https://mlsanity.com/paper/1310.5569/) (2013)

## Built on by (most cited first, 2 of 2)

- [Does Feedback Help in Bandits with Arm Erasures?](https://mlsanity.com/paper/2504.20894/) (2025)
- [Best-Arm Identification with Noisy Actuation](https://mlsanity.com/paper/2604.02255/) (2026)

## Abstract (arXiv)

Multi-Armed Bandit (MAB) systems are witnessing an upswing in applications within multi-agent distributed environments, leading to the advancement of collaborative MAB algorithms. In such settings, communication between agents executing actions and the primary learner making decisions can hinder the learning process. A prevalent challenge in distributed learning is action erasure, often induced by communication delays and/or channel noise. This results in agents possibly not receiving the intended action from the learner, subsequently leading to misguided feedback. In this paper, we introduce novel algorithms that enable learners to interact concurrently with distributed agents across heterogeneous action erasure channels with different action erasure probabilities. We illustrate that, in contrast to existing bandit algorithms, which experience linear regret, our algorithms assure sub-linear regret guarantees. Our proposed solutions are founded on a meticulously crafted repetition protocol and scheduling of learning across heterogeneous channels. To our knowledge, these are the first algorithms capable of effectively learning through heterogeneous action erasure channels. We substantiate the superior performance of our algorithm through numerical experiments, emphasizing their practical significance in addressing issues related to communication constraints and delays in multi-agent environments.