# Multiplayer Information Asymmetric Contextual Bandits

arXiv: https://arxiv.org/abs/2503.08961 · HTML: https://mlsanity.com/paper/2503.08961/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 21 of 21)

- [Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits](https://mlsanity.com/paper/1402.0555/) (2014)
- [Linear Contextual Bandits with Knapsacks](https://mlsanity.com/paper/1507.06738/) (2015)
- [Delay and Cooperation in Nonstochastic Bandits](https://mlsanity.com/paper/1602.04741/) (2016)
- [Competing Bandits in Matching Markets](https://mlsanity.com/paper/1906.05363/) (2019)
- [Bandit Learning in Decentralized Matching Markets](https://mlsanity.com/paper/2012.07348/) (2020)
- [Resourceful Contextual Bandits](https://mlsanity.com/paper/1402.6779/) (2014)
- [Collaborative Learning with Limited Interaction: Tight Bounds for Distributed Exploration in Multi-Armed Bandits](https://mlsanity.com/paper/1904.03293/) (2019)
- [Learning Equilibria in Matching Markets from Bandit Feedback](https://mlsanity.com/paper/2108.08843/) (2021)
- [On Distributed Cooperative Decision-Making in Multiarmed Bandits](https://mlsanity.com/paper/1512.06888/) (2015)
- [A Neural Networks Committee for the Contextual Bandit Problem](https://mlsanity.com/paper/1409.8191/) (2014)
- [Cooperative Online Learning: Keeping your Neighbors Updated](https://mlsanity.com/paper/1901.08082/) (2019)
- [Collaborative Top Distribution Identifications with Limited Interaction](https://mlsanity.com/paper/2004.09454/) (2020)
- [Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits](https://mlsanity.com/paper/1907.03346/) (2019)
- [Regret, stability & fairness in matching markets with bandit learners](https://mlsanity.com/paper/2102.06246/) (2021)
- [Multi-Armed Bandit Learning in IoT Networks: Learning helps even in non-stationary settings](https://mlsanity.com/paper/1807.00491/) (2018)
- [Context Attentive Bandits: Contextual Bandit with Restricted Context](https://mlsanity.com/paper/1705.03821/) (2017)
- [Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure](https://mlsanity.com/paper/2111.00781/) (2021)
- [Multiplayer Bandit Learning, from Competition to Cooperation](https://mlsanity.com/paper/1908.01135/) (2019)
- [Online Learning for Cooperative Multi-Player Multi-Armed Bandits](https://mlsanity.com/paper/2109.03818/) (2021)
- [Reinforcement Learning Algorithm Selection](https://mlsanity.com/paper/1701.08810/) (2017)
- [An Optimal Algorithm for Multiplayer Multi-Armed Bandits](https://mlsanity.com/paper/1909.13079/) (2019)

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

- [Bayesian Decision Making around Experts](https://mlsanity.com/paper/2510.08113/) (2025)
- [DCM Bandits: Multiplayer Information Asymmetric Cascading Bandits for Multiple Clicks](https://mlsanity.com/paper/2608.11873/) (2026)
- [Improved Multiplayer Bandit Algorithm for Bernoulli Rewards](https://mlsanity.com/paper/2609.26213/) (2026)

## Abstract (arXiv)

Single-player contextual bandits are a well-studied problem in reinforcement learning that has seen applications in various fields such as advertising, healthcare, and finance. In light of the recent work on information asymmetric bandits citechang2022online, chang2023online, we propose a novel multiplayer information asymmetric contextual bandit framework where there are multiple players each with their own set of actions. At every round, they observe the same context vectors and simultaneously take an action from their own set of actions, giving rise to a joint action. However, upon taking this action the players are subjected to information asymmetry in (1) actions and/or (2) rewards. We designed an algorithm textttLinUCB by modifying the classical single-player algorithm textttLinUCB in citechu2011contextual to achieve the optimal regret O(√T) when only one kind of asymmetry is present. We then propose a novel algorithm textttETC that is built on explore-then-commit principles to achieve the same optimal regret when both types of asymmetry are present.