# Learning under Opponent Unawareness in Linear-Quadratic Stochastic Games

arXiv: https://arxiv.org/abs/2608.08268 · HTML: https://mlsanity.com/paper/2608.08268/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 50 references that are in the map.
- First posted on arXiv 8 Aug 2026.

## Builds on (most cited first, 18 of 18)

- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator](https://mlsanity.com/paper/1801.05039/) (2018)
- [Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification](https://mlsanity.com/paper/1802.08334/) (2018)
- [Naive Exploration is Optimal for Online LQR](https://mlsanity.com/paper/2001.09576/) (2020)
- [What Doubling Tricks Can and Can't Do for Multi-Armed Bandits](https://mlsanity.com/paper/1803.06971/) (2018)
- [Decentralized Q-Learning in Zero-sum Markov Games](https://mlsanity.com/paper/2106.02748/) (2021)
- [Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions](https://mlsanity.com/paper/2410.00031/) (2024)
- [Policy Gradient Methods Find the Nash Equilibrium in N-player General-sum Linear-quadratic Games](https://mlsanity.com/paper/2107.13090/) (2021)
- [Independent Learning in Stochastic Games](https://mlsanity.com/paper/2111.11743/) (2021)
- [Independent and Decentralized Learning in Markov Potential Games](https://mlsanity.com/paper/2205.14590/) (2022)
- [Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games](https://mlsanity.com/paper/1907.03712/) (2019)
- [Doubly Optimal No-Regret Online Learning in Strongly Monotone Games with Bandit Feedback](https://mlsanity.com/paper/2112.02856/) (2021)
- [Learning with minimal information in continuous games](https://mlsanity.com/paper/1806.11506/) (2018)
- [Multi-Agent Reinforcement Learning in Cournot Games](https://mlsanity.com/paper/2009.06224/) (2020)
- [Learning Distributed Equilibria in Linear-Quadratic Stochastic Differential Games: An α-Potential Approach](https://mlsanity.com/paper/2602.16555/) (2026)
- [Linear Quadratic Stochastic Two-Person Nonzero-Sum Differential Games: Open-Loop and Closed-Loop Nash Equilibria](https://mlsanity.com/paper/1607.04526/) (2016)
- [Is Thompson Sampling Susceptible to Algorithmic Collusion?](https://mlsanity.com/paper/2405.17463/) (2024)
- [Strategic AI in Cournot Markets](https://mlsanity.com/paper/2601.17263/) (2026)

## Abstract (arXiv)

As firms increasingly deploy machine learning for strategic decision-making, understanding algorithmic interactions has become central to operations research and economics. This paper studies learning in infinite-horizon, nonzero-sum linear-quadratic stochastic games under a radically uncoupled information structure, where players are either unaware of opponents or strategically oblivious, observing only a common state and their own action history. Under this minimal information, we analyze an asynchronous decentralized learning process in which each player independently runs a single-agent ε-greedy iterated least-squares algorithm. We prove that, despite being unable to identify the system parameters, players' learning dynamics converge almost surely to the complete-information Nash equilibrium and characterize the convergence rate. We then apply the framework to a dynamic Cournot competition with sticky prices. Numerical experiments validate the theoretical results and show that learning under limited information reduces firm profits under both low and high price stickiness, while total surplus declines and market concentration increases when price stickiness is high. Publicly revealing aggregate market output substantially accelerates convergence and mitigates these welfare losses.