Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2609.21944

Guiding Agents of Quantum Games to Equilibrium using Matrix Exponential Fixed-Point Iteration

Alireza Habibi, Luis F. Abanto Leon, Setareh Maghsudi

quant-phcs.GTcs.LGcs.MASubmitted Sep 18, 2026• Announced Sep 21, 2026• 0 citations
arXivHTMLPDF

Abstract

In recent years, quantum game theory has gained significant attention as a framework for studying decision-making in multi-agent systems using quantum principles. However, computing equilibrium strategies is challenging because the dimension of the joint Hilbert space grows as the product of the players' local dimensions. In this paper, we consider an extended Gutoski-Watrous (EGW) game in which each player's quantum strategy is represented by a local density matrix. We derive tensor-contraction expressions for the payoff functions and their gradients, thereby avoiding the explicit construction of the full joint density matrix and its computationally expensive multiplication by the payoff operators. Building on the resulting effective Hamiltonians, we propose the Matrix Exponential Fixed-Point Iteration with Annealing (MEFPIA) algorithm to search for equilibrium points in EGW games. We compare MEFPIA with the Matrix Multiplicative Weights Update (MMWU) algorithm in terms of convergence. For the tested instances and parameter settings, both algorithms approach the same strategy profiles and payoffs, while MEFPIA achieves lower relative error in fewer iterations. These results indicate that MEFPIA is a promising numerical method for equilibrium search in multi-agent quantum games. Our findings provide important insights into the quantum game theory's potential for addressing complex decision-making processes, as well as opening up new paths for future research and exploration in multi-agent quantum systems.

AI Summary

The paper studies numerical Nash-equilibrium search in multiplayer noninteractive quantum games, where each player chooses a local density matrix and payoffs are expectations of joint reward operators on the product strategy profile. It derives tensor-contraction expressions for payoffs and effective local Hamiltonians, avoiding explicit construction of the joint density matrix. Relative to evaluating full matrix products, the stated payoff-evaluation cost decreases from $O(\prod_i d_i^3)$ to $O((N+1)\prod_i d_i^2)$; sparse reward operators also permit reduced storage. The proposed Matrix Exponential Fixed-Point Iteration with Annealing (MEFPIA) simultaneously updates players using entropy-regularized best responses, $\rho_i\propto\exp(-H_i/T)$, while decreasing $T$. The Gibbs response is established as the unique regularized optimum using quantum relative entropy. If the strategy iterates converge while $T\to0$, their limit is a Nash equilibrium; convergence of the iteration itself is not established. Numerical comparisons with matrix multiplicative weights use 100 random initial profiles. Tests include two-qubit Prisoner’s-Dilemma variants with product or entangled projective measurements, and a three-player game with local dimension five and 27 product POVM outcomes. In the tested settings, MEFPIA reaches lower relative payoff error in fewer iterations. The simplest test reaches approximately $10^{-16}$ error within 100 iterations; the entangled-measurement test reports payoff $2.25$ per player. The larger test uses commuting local POVMs and yields mixed limiting states with purity approximately $1/2$. The evidence is restricted to these instances and parameter choices. Cooling-rate sensitivity is examined, while convergence properties, larger games, and more general measurement structures remain future work.

Little sign of AI-generated textAI use disclosedIncrementalSmall numerics onlyUnclear noveltyOverclaims
ChatGPT and QuillBot were used to improve the language and readability of this paper.

Central claim may not hold: In Experiment 1's Bell-outcome game, the reported pure limiting strategies with payoff 2.25 cannot be a Nash equilibrium because each player can obtain at least 2.5 by best responding to the other's pure strategy. The relative-payoff-error metric cannot certify equilibrium or convergence to the same strategy profiles, and the specified Bell-outcome game admits profiles with zero reported payoff error but a profitable unilateral deviation.

Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.

Related papers

Riemannian Optimization for Multi-Player Quantum Games on Product Unitary Manifolds

Alireza Habibi, Setareh Maghsudi

Quantum game theory is an extension of classical game theory that uses quantum principles in game theory. The Eisert-Wilkens-Lewenstein (EWL) quantum game is an early example of the two-player classical Prisoner's Dilemma transformed into a quantum Prisoner's Dilemma. In the EWL game, the players choose pure quantum strategies represented by unitary matrices. This extension can resolve the classical dilemma by enabling cooperative equilibrium with higher payoff. In this paper, we first discuss the Extended EWL (EEWL) for multiplayer quantum games with mixed strategies. In EEWL, each player controls a set of unitary operators as quantum actions and uses a classical mixed strategy over these actions. The payoffs are defined as expectation values of Hermitian reward operators acting on a shared quantum state, which is generated and measured according to the EEWL protocol. We then propose the Unitary Strategy Matrix Exponential Algorithm (USMEA), a geometry-aware sequential algorithm for the EEWL mixed-strategy setting, in which each player jointly learns a trainable set of local unitary actions and the associated classical mixing probabilities. Thereby it acts as a learning-and-control layer for multi-agent quantum decision systems. We analyze the convergence properties of USMEA under standard smoothness and step-size conditions and validate the theory with numerical experiments. These results show how classical optimization methods can be systematically integrated into the design and analysis of engineered quantum strategic interactions.

quant-pharXiv:2609.07397•IEEE Transactions on Quantum Engineering•Sep 8, 2026•0 citations

A Quadratic Speedup in Finding Nash Equilibria of Quantum Zero-Sum Games

Francisca Vasconcelos, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Panayotis Mertikopoulos +2 more

Recent developments in domains such as non-local games, quantum interactive proofs, and quantum generative adversarial networks have renewed interest in quantum game theory and, specifically, quantum zero-sum games. Central to classical game theory is the efficient algorithmic computation of Nash equilibria, which represent optimal strategies for both players. In 2008, Jain and Watrous proposed the first classical algorithm for computing equilibria in quantum zero-sum games using the Matrix Multiplicative Weight Updates (MMWU) method to achieve a convergence rate of O(d/ϵ2) iterations to ϵ -Nash equilibria in the 4d -dimensional spectraplex. In this work, we propose a hierarchy of quantum optimization algorithms that generalize MMWU via an extra-gradient mechanism. Notably, within this proposed hierarchy, we introduce the Optimistic Matrix Multiplicative Weights Update (OMMWU) algorithm and establish its average-iterate convergence complexity as O(d/ϵ) iterations to ϵ -Nash equilibria. This quadratic speed-up relative to Jain and Watrous' original algorithm sets a new benchmark for computing ϵ -Nash equilibria in quantum zero-sum games.

arXiv:2311.10859•Quantum•May 6, 2025•5 citations

Payoff-based learning with matrix multiplicative weights in quantum games

Kyriakos Lotidis, Panayotis Mertikopoulos, Nicholas Bambos +1 more

In this paper, we study the problem of learning in quantum games - and other classes of semidefinite games - with scalar, payoff-based feedback. For concreteness, we focus on the widely used matrix multiplicative weights (MMW) algorithm and, instead of requiring players to have full knowledge of the game (and/or each other's chosen states), we introduce a suite of minimal-information matrix multiplicative weights (3MW) methods tailored to different information frameworks. The main difficulty to attaining convergence in this setting is that, in contrast to classical finite games, quantum games have an infinite continuum of pure states (the quantum equivalent of pure strategies), so standard importance-weighting techniques for estimating payoff vectors cannot be employed. Instead, we borrow ideas from bandit convex optimization and we design a zeroth-order gradient sampler adapted to the semidefinite geometry of the problem at hand. As a first result, we show that the 3MW method with deterministic payoff feedback retains the $\mathcal{O}(1/\sqrt{T})$ convergence rate of the vanilla, full information MMW algorithm in quantum min-max games, even though the players only observe a single scalar. Subsequently, we relax the algorithm's information requirements even further and we provide a 3MW method that only requires players to observe a random realization of their payoff observable, and converges to equilibrium at an $\mathcal{O}(T^{-1/4})$ rate. Finally, going beyond zero-sum games, we show that a regularized variant of the proposed 3MW method guarantees local convergence with high probability to all equilibria that satisfy a certain first-order stability condition.

arXiv:2311.02423•Nov 4, 2023•1 citation

Payoff-based learning with matrix multiplicative weights in quantum games

Kyriakos Lotidis, Panayotis Mertikopoulos, Nicholas Bambos +1 more

In this paper, we study the problem of learning in quantum gamesand other classes of semidefinite games-with scalar, payoff-based feedback. For concreteness, we focus on the widely used matrix multiplicative weights (MMW) algorithm and, instead of requiring players to have full knowledge of the game (and/or each other's chosen states), we introduce a suite of minimal-information matrix multiplicative weights (3MW) methods tailored to different information frameworks. The main difficulty to attaining convergence in this setting is that, in contrast to classical finite games, quantum games have an infinite continuum of pure states (the quantum equivalent of pure strategies), so standard importance-weighting techniques for estimating payoff vectors cannot be employed. Instead, we borrow ideas from bandit convex optimization and we design a zeroth-order gradient sampler adapted to the semidefinite geometry of the problem at hand. As a first result, we show that the 3MW method with deterministic payoff feedback retains the O(1/ √ T) convergence rate of the vanilla, full information MMW algorithm in quantum min-max games, even though the players only observe a single scalar. Subsequently, we relax the algorithm's information requirements even further and we provide a 3MW method that only requires players to observe a random realization of their payoff observable, and converges to equilibrium at an O(T −1/4) rate. Finally, going beyond zero-sum games, we show that a regularized variant of the proposed 3MW method guarantees local convergence with high probability to all equilibria that satisfy a certain first-order stability condition.

•Dec 10, 2023•0 citations

Graph-encoded strategic interactions in multiplayer quantum games

Michael Tsakiroglou, Ioannis Liliopoulos, Georgios D. Varsamis +2 more

Abstract Multiplayer quantum games have received growing attention due to the ability of quantum computational models to access enlarged strategic spaces, thereby enabling the emergence of nonclassical Nash equilibria and Pareto-efficient solutions. Concurrently, graph-theoretic representations have become a standard tool for encoding relational dependencies among interacting players. This work establishes a unified formalism that embeds arbitrary graph topologies into parametrized quantum-game circuits, providing a direct mapping between network structure and the strategic interaction space of quantum players. Within this framework, we analytically and computationally evaluate how graph-induced interpersonal couplings modulate payoff distributions over repeated quantum-game iterations. In addition, we integrate a reward-driven adaptation algorithm that allows players to optimize their local strategy parameters dynamically with respect to accumulated payoffs. Experimental results demonstrate that the equilibrium reward landscape is highly sensitive to the players’ graph-theoretic centrality and the weighted structure of their adversarial and cooperative relationships.

Quantum Information Processing•Mar 23, 2026•1 citation

Nash Equilibrium Improvement in Quantum Extensions of Symmetric Games

Anna Gorczyca–Goraj, Krzysztof Grzegorz Grzanka, Piotr Frąckiewicz +2 more

Abstract Quantum strategies can alter the equilibrium structure of classical games, but apparent improvements may depend on arbitrary strategy labels or on the particular quantum operations admitted. Here, we characterize payoff improvement across all permissible three-strategy extensions of renaming-symmetric \(2 \times 2\) games within the Eisert-Wilkens-Lewenstein framework. We preserve the classical game as a subgame and add one fixed unitary strategy, restricting attention to the three extension classes that remain invariant under isomorphic transformations of the classical game. Across six canonical payoff orderings, including coordination, anti-coordination, and dominant-strategy dilemmas, we derive the conditions under which the extended games admit pure Nash equilibria whose payoffs are no lower than those of the corresponding symmetric classical equilibrium. The classical-type \(A_0\) extension produces no strict improvement, while \(B_0\) does so only in restricted regions and generally asymmetrically. By contrast, the genuinely quantum \(C_0\) extension supports non-inferior equilibria across all six classes and yields strict, mutually beneficial improvements in identifiable payoff regions. These results move beyond isolated game examples by showing precisely when representation-invariant quantum extensions can improve equilibrium payoffs and when they cannot. These conditions provide a design map for quantum-enabled multi-agent protocols by identifying the payoff structures under which an added quantum strategy can improve equilibrium outcomes without altering the players' underlying preferences.

•Aug 6, 2026•0 citations
In recent years, quantum game theory has gained significant attention as a framework for studying decision-making in multi-agent systems using quantum principles. However, computing equilibrium strategies is challenging because the dimension of the joint Hilbert space grows as the product of the players' local dimensions. In this paper, we consider an extended Gutoski-Watrous (EGW) game in which each player's quantum strategy is represented by a local density matrix. We derive tensor-contraction expressions for the payoff functions and their gradients, thereby avoiding the explicit construction of the full joint density matrix and its computationally expensive multiplication by the payoff operators. Building on the resulting effective Hamiltonians, we propose the Matrix Exponential Fixed-Point Iteration with Annealing (MEFPIA) algorithm to search for equilibrium points in EGW games. We compare MEFPIA with the Matrix Multiplicative Weights Update (MMWU) algorithm in terms of convergence. For the tested instances and parameter settings, both algorithms approach the same strategy profiles and payoffs, while MEFPIA achieves lower relative error in fewer iterations. These results indicate that MEFPIA is a promising numerical method for equilibrium search in multi-agent quantum games. Our findings provide important insights into the quantum game theory's potential for addressing complex decision-making processes, as well as opening up new paths for future research and exploration in multi-agent quantum systems.
The paper studies numerical Nash-equilibrium search in multiplayer noninteractive quantum games, where each player chooses a local density matrix and payoffs are expectations of joint reward operators on the product strategy profile. It derives tensor-contraction expressions for payoffs and effective local Hamiltonians, avoiding explicit construction of the joint density matrix. Relative to evaluating full matrix products, the stated payoff-evaluation cost decreases from O(∏idi3)O(\prod_i d_i^3)O(∏i​di3​) to O((N+1)∏idi2)O((N+1)\prod_i d_i^2)O((N+1)∏i​di2​); sparse reward operators also permit reduced storage.
The proposed Matrix Exponential Fixed-Point Iteration with Annealing (MEFPIA) simultaneously updates players using entropy-regularized best responses, ρi∝exp⁡(−Hi/T)\rho_i\propto\exp(-H_i/T)ρi​∝exp(−Hi​/T), while decreasing TTT. The Gibbs response is established as the unique regularized optimum using quantum relative entropy. If the strategy iterates converge while T→0T\to0T→0, their limit is a Nash equilibrium; convergence of the iteration itself is not established.
Numerical comparisons with matrix multiplicative weights use 100 random initial profiles. Tests include two-qubit Prisoner’s-Dilemma variants with product or entangled projective measurements, and a three-player game with local dimension five and 27 product POVM outcomes. In the tested settings, MEFPIA reaches lower relative payoff error in fewer iterations. The simplest test reaches approximately 10−1610^{-16}10−16 error within 100 iterations; the entangled-measurement test reports payoff 2.252.252.25 per player. The larger test uses commuting local POVMs and yields mixed limiting states with purity approximately 1/21/21/2.
The evidence is restricted to these instances and parameter choices. Cooling-rate sensitivity is examined, while convergence properties, larger games, and more general measurement structures remain future work.
Quantum game theory is an extension of classical game theory that uses quantum principles in game theory. The Eisert-Wilkens-Lewenstein (EWL) quantum game is an early example of the two-player classical Prisoner's Dilemma transformed into a quantum Prisoner's Dilemma. In the EWL game, the players choose pure quantum strategies represented by unitary matrices. This extension can resolve the classical dilemma by enabling cooperative equilibrium with higher payoff. In this paper, we first discuss the Extended EWL (EEWL) for multiplayer quantum games with mixed strategies. In EEWL, each player controls a set of unitary operators as quantum actions and uses a classical mixed strategy over these actions. The payoffs are defined as expectation values of Hermitian reward operators acting on a shared quantum state, which is generated and measured according to the EEWL protocol. We then propose the Unitary Strategy Matrix Exponential Algorithm (USMEA), a geometry-aware sequential algorithm for the EEWL mixed-strategy setting, in which each player jointly learns a trainable set of local unitary actions and the associated classical mixing probabilities. Thereby it acts as a learning-and-control layer for multi-agent quantum decision systems. We analyze the convergence properties of USMEA under standard smoothness and step-size conditions and validate the theory with numerical experiments. These results show how classical optimization methods can be systematically integrated into the design and analysis of engineered quantum strategic interactions.
Recent developments in domains such as non-local games, quantum interactive proofs, and quantum generative adversarial networks have renewed interest in quantum game theory and, specifically, quantum zero-sum games. Central to classical game theory is the efficient algorithmic computation of Nash equilibria, which represent optimal strategies for both players. In 2008, Jain and Watrous proposed the first classical algorithm for computing equilibria in quantum zero-sum games using the Matrix Multiplicative Weight Updates (MMWU) method to achieve a convergence rate of O(d/ϵ2) iterations to ϵ -Nash equilibria in the 4d -dimensional spectraplex. In this work, we propose a hierarchy of quantum optimization algorithms that generalize MMWU via an extra-gradient mechanism. Notably, within this proposed hierarchy, we introduce the Optimistic Matrix Multiplicative Weights Update (OMMWU) algorithm and establish its average-iterate convergence complexity as O(d/ϵ) iterations to ϵ -Nash equilibria. This quadratic speed-up relative to Jain and Watrous' original algorithm sets a new benchmark for computing ϵ -Nash equilibria in quantum zero-sum games.
In this paper, we study the problem of learning in quantum games - and other classes of semidefinite games - with scalar, payoff-based feedback. For concreteness, we focus on the widely used matrix multiplicative weights (MMW) algorithm and, instead of requiring players to have full knowledge of the game (and/or each other's chosen states), we introduce a suite of minimal-information matrix multiplicative weights (3MW) methods tailored to different information frameworks. The main difficulty to attaining convergence in this setting is that, in contrast to classical finite games, quantum games have an infinite continuum of pure states (the quantum equivalent of pure strategies), so standard importance-weighting techniques for estimating payoff vectors cannot be employed. Instead, we borrow ideas from bandit convex optimization and we design a zeroth-order gradient sampler adapted to the semidefinite geometry of the problem at hand. As a first result, we show that the 3MW method with deterministic payoff feedback retains the O(1/T)\mathcal{O}(1/\sqrt{T})O(1/T​) convergence rate of the vanilla, full information MMW algorithm in quantum min-max games, even though the players only observe a single scalar. Subsequently, we relax the algorithm's information requirements even further and we provide a 3MW method that only requires players to observe a random realization of their payoff observable, and converges to equilibrium at an O(T−1/4)\mathcal{O}(T^{-1/4})O(T−1/4) rate. Finally, going beyond zero-sum games, we show that a regularized variant of the proposed 3MW method guarantees local convergence with high probability to all equilibria that satisfy a certain first-order stability condition.
In this paper, we study the problem of learning in quantum gamesand other classes of semidefinite games-with scalar, payoff-based feedback. For concreteness, we focus on the widely used matrix multiplicative weights (MMW) algorithm and, instead of requiring players to have full knowledge of the game (and/or each other's chosen states), we introduce a suite of minimal-information matrix multiplicative weights (3MW) methods tailored to different information frameworks. The main difficulty to attaining convergence in this setting is that, in contrast to classical finite games, quantum games have an infinite continuum of pure states (the quantum equivalent of pure strategies), so standard importance-weighting techniques for estimating payoff vectors cannot be employed. Instead, we borrow ideas from bandit convex optimization and we design a zeroth-order gradient sampler adapted to the semidefinite geometry of the problem at hand. As a first result, we show that the 3MW method with deterministic payoff feedback retains the O(1/ √ T) convergence rate of the vanilla, full information MMW algorithm in quantum min-max games, even though the players only observe a single scalar. Subsequently, we relax the algorithm's information requirements even further and we provide a 3MW method that only requires players to observe a random realization of their payoff observable, and converges to equilibrium at an O(T −1/4) rate. Finally, going beyond zero-sum games, we show that a regularized variant of the proposed 3MW method guarantees local convergence with high probability to all equilibria that satisfy a certain first-order stability condition.
Abstract Multiplayer quantum games have received growing attention due to the ability of quantum computational models to access enlarged strategic spaces, thereby enabling the emergence of nonclassical Nash equilibria and Pareto-efficient solutions. Concurrently, graph-theoretic representations have become a standard tool for encoding relational dependencies among interacting players. This work establishes a unified formalism that embeds arbitrary graph topologies into parametrized quantum-game circuits, providing a direct mapping between network structure and the strategic interaction space of quantum players. Within this framework, we analytically and computationally evaluate how graph-induced interpersonal couplings modulate payoff distributions over repeated quantum-game iterations. In addition, we integrate a reward-driven adaptation algorithm that allows players to optimize their local strategy parameters dynamically with respect to accumulated payoffs. Experimental results demonstrate that the equilibrium reward landscape is highly sensitive to the players’ graph-theoretic centrality and the weighted structure of their adversarial and cooperative relationships.
Abstract Quantum strategies can alter the equilibrium structure of classical games, but apparent improvements may depend on arbitrary strategy labels or on the particular quantum operations admitted. Here, we characterize payoff improvement across all permissible three-strategy extensions of renaming-symmetric 2×22 \times 22×2 games within the Eisert-Wilkens-Lewenstein framework. We preserve the classical game as a subgame and add one fixed unitary strategy, restricting attention to the three extension classes that remain invariant under isomorphic transformations of the classical game. Across six canonical payoff orderings, including coordination, anti-coordination, and dominant-strategy dilemmas, we derive the conditions under which the extended games admit pure Nash equilibria whose payoffs are no lower than those of the corresponding symmetric classical equilibrium. The classical-type A0A_0A0​ extension produces no strict improvement, while B0B_0B0​ does so only in restricted regions and generally asymmetrically. By contrast, the genuinely quantum C0C_0C0​ extension supports non-inferior equilibria across all six classes and yields strict, mutually beneficial improvements in identifiable payoff regions. These results move beyond isolated game examples by showing precisely when representation-invariant quantum extensions can improve equilibrium payoffs and when they cannot. These conditions provide a design map for quantum-enabled multi-agent protocols by identifying the payoff structures under which an added quantum strategy can improve equilibrium outcomes without altering the players' underlying preferences.