# On Information Asymmetry in Competitive Multi-Agent Reinforcement Learning: Convergence and Optimality

arXiv: https://arxiv.org/abs/2010.10901 · HTML: https://mlsanity.com/paper/2010.10901/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2020.

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

- [Can Competition Enhance the Proficiency of Agents Powered by Large Language Models in the Realm of News-driven Time Series Forecasting?](https://mlsanity.com/paper/2504.10210/) (2025)

## Abstract (arXiv)

In this work, we study the system of interacting non-cooperative two Q-learning agents, where one agent has the privilege of observing the other's actions. We show that this information asymmetry can lead to a stable outcome of population learning, which generally does not occur in an environment of general independent learners. The resulting post-learning policies are almost optimal in the underlying game sense, i.e., they form a Nash equilibrium. Furthermore, we propose in this work a Q-learning algorithm, requiring predictive observation of two subsequent opponent's actions, yielding an optimal strategy given that the latter applies a stationary strategy, and discuss the existence of the Nash equilibrium in the underlying information asymmetrical game.