# Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams

arXiv: https://arxiv.org/abs/2110.00751 · HTML: https://mlsanity.com/paper/2110.00751/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 2 Oct 2021.

## Builds on (most cited first, 12 of 12)

- [Learning with Opponent-Learning Awareness](https://mlsanity.com/paper/1709.04326/) (2017)
- [Learning Latent Representations to Influence Multi-Agent Interaction](https://mlsanity.com/paper/2011.06619/) (2020)
- [Distributed Cooperative Decision-Making in Multiarmed Bandits: Frequentist and Bayesian Algorithms](https://mlsanity.com/paper/1606.00911/) (2016)
- [Learning Policy Representations in Multiagent Systems](https://mlsanity.com/paper/1806.06464/) (2018)
- [Social Learning in Multi Agent Multi Armed Bandits](https://mlsanity.com/paper/1910.02100/) (2019)
- [On the Critical Role of Conventions in Adaptive Human-AI Collaboration](https://mlsanity.com/paper/2104.02871/) (2021)
- [Multi-Agent Safe Planning with Gaussian Processes](https://mlsanity.com/paper/2008.04452/) (2020)
- [Efficient and Trustworthy Social Navigation Via Explicit and Implicit Robot-Human Communication](https://mlsanity.com/paper/1810.11556/) (2018)
- [Learning from My Partner's Actions: Roles in Decentralized Robot Teams](https://mlsanity.com/paper/1910.07613/) (2019)
- [Heterogeneous Stochastic Interactions for Multiple Agents in a Multi-armed Bandit Problem](https://mlsanity.com/paper/1905.08731/) (2019)
- [Building Second-Order Mental Models for Human-Robot Interaction](https://mlsanity.com/paper/1909.06508/) (2019)
- [Decentralized Cooperative Stochastic Bandits](https://mlsanity.com/paper/1810.04468/) (2018)

## Built on by (most cited first, 1 of 1)

- [Decentralized Online Bandit Optimization on Directed Graphs with Regret Bounds](https://mlsanity.com/paper/2301.11802/) (2023)

## Abstract (arXiv)

When humans collaborate with each other, they often make decisions by observing others and considering the consequences that their actions may have on the entire team, instead of greedily doing what is best for just themselves. We would like our AI agents to effectively collaborate in a similar way by capturing a model of their partners. In this work, we propose and analyze a decentralized Multi-Armed Bandit (MAB) problem with coupled rewards as an abstraction of more general multi-agent collaboration. We demonstrate that na"ive extensions of single-agent optimal MAB algorithms fail when applied for decentralized bandit teams. Instead, we propose a Partner-Aware strategy for joint sequential decision-making that extends the well-known single-agent Upper Confidence Bound algorithm. We analytically show that our proposed strategy achieves logarithmic regret, and provide extensive experiments involving human-AI and human-robot collaboration to validate our theoretical findings. Our results show that the proposed partner-aware strategy outperforms other known methods, and our human subject studies suggest humans prefer to collaborate with AI agents implementing our partner-aware strategy.