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:2606.03109

Game, Set, Quantum: Parameterized Quantum Circuit for Correlated Equilibrium in Bayesian Games

Param Pathak, Vidhi Oad, Nouhaila Innan, Adarsh Ganesan, Muhammad Shafique

On Aqora:Muhammad ShafiqueMuhammad Shafique
quant-phSubmitted Jun 2, 2026• Announced Jun 3, 2026• 0 citations• Revised Aug 21, 2026 (v2)
v1 · Jun 2, 2026v2 · Aug 21, 2026
arXivHTMLPDF

Abstract

Strategic decision-making among many agents under incomplete information is central to economics, security, and multi-agent artificial intelligence (AI). Computing equilibria in such settings is challenging because the joint type-action space grows exponentially with the number of players. In binary-type, binary-action Bayesian games with $n$ players, an explicit representation over type-action profiles requires $O(2^{2n})$ entries, making direct linear-programming (LP) formulations increasingly costly as $n$ grows. We propose a hybrid quantum-classical framework for approximating Bayes correlated equilibrium (BCE) using a parameterized quantum circuit (PQC). The PQC represents the conditional distribution over joint actions using $O(nL)$ trainable parameters, where $L$ denotes the circuit depth; for the largest trained setting, $n=8$ and $L=2$, this corresponds to $48$ trainable angles. Each player count is trained independently by maximizing expected social welfare with a penalty on positive aggregated BCE obedience violations. On a strategically coupled Bayesian congestion game with $n=2,4,6,8$ players, feasible PQC solutions attain higher welfare than MCCFR and DCFR product-strategy baselines while satisfying $ε_{\max}\leq10^{-3}$, where $ε_{\max}$ denotes the maximum positive aggregated BCE obedience violation. Across five independent runs per setting, all runs are feasible for $n=2,4,6$, while four of five are feasible for $n=8$. PQC welfare remains below the exact LP optimum, with the absolute gap increasing with $n$, while classical state-vector simulation prevents PQC training beyond eight players. These results demonstrate the use of a compact PQC parameterization for approximate equilibrium computation and quantify its welfare, feasibility, and classical simulation scaling on the studied benchmark.

Comments
35 pages, 8 figures

Related papers

Demonstration of a Bayesian quantum game on an ion-trap quantum computer

Neal Solmeyer, Norbert M. Linke, Caroline Figgatt +4 more

Abstract We demonstrate a Bayesian quantum game on an ion-trap quantum computer with five qubits. The players share an entangled pair of qubits and perform rotations on their qubit as the strategy choice. Two five-qubit circuits are sufficient to run all 16 possible strategy choice sets in a game with four possible strategies. The data are then parsed into player types randomly in order to combine them classically into a Bayesian framework. We exhaustively compute the possible strategies of the game so that the experimental data can be used to solve for the Nash equilibria of the game directly. Then we compare the payoff at the Nash equilibria and location of discontinuous changes in the payoff obtained from the experimental data to the theory, and study how it changes as a function of the amount of entanglement.

arXiv:1802.08116•Quantum Science and Technology•Jun 26, 2018•12 citations

Parameterized Quantum Circuits for Deep Reinforcement Learning

Hrvoje Kukina, Susanne F. Yelin

Deep reinforcement learning (DRL) is a standard approach to sequential decision-making under uncertainty, where value functions are often approximated with deep neural networks such as Deep Q-Networks (DQNs). Parameterized quantum circuits (PQCs) have emerged as a flexible modeling primitive for near-term quantum hardware, enabling hybrid quantum–classical predictors in which a PQC produces bounded expectation-value features that are processed by classical layers. A practical limitation of many quantum learning approaches, however, is the need for quantum hardware not only during training but also at deployment time. In this work, we study PQC-driven value-based agents in the CartPole control benchmark. Using a common DQN-style training loop, we compare classical DQN baselines, a PQC-based Q-network, and a hybrid workflow that leverages classical shadows for evaluation-only deployment. To probe near-term practicality, we further examine robustness by injecting additive Gaussian perturbations into the quantum feature vector across multiple noise amplitudes.

IEEE International Conference on Quantum Control, Computing and Learning (qCCL)•Jun 1, 2026•0 citations

Characterizing the Nash equilibria of three-player Bayesian quantum games

Neal Solmeyer, Radhakrishnan Balu

Quantum games with incomplete information can be studied within a Bayesian framework. We analyze games quantized within the EWL framework [Eisert, Wilkens, and Lewenstein, Phys Rev. Lett. 83, 3077 (1999)]. We solve for the Nash equilibria of a variety of two-player quantum games and compare the results to the solutions of the corresponding classical games. We then analyze Bayesian games where there is uncertainty about the player types in two-player conflicting interest games. The solutions to the Bayesian games are found to have a phase diagram-like structure where different equilibria exist in different parameter regions, depending both on the amount of uncertainty and the degree of entanglement. We find that in games where a Pareto-optimal solution is not a Nash equilibrium, it is possible for the quantized game to have an advantage over the classical version. In addition, we analyze the behavior of the solutions as the strategy choices approach an unrestricted operation. We find that some games have a continuum of solutions, bounded by the solutions of a simpler restricted game. A deeper understanding of Bayesian quantum game theory could lead to novel quantum applications in a multi-agent setting.

arXiv:1703.03292•Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE•May 5, 2017•6 citations

Near-Optimal Quantum Algorithms for Computing (Coarse) Correlated Equilibria of General-Sum Games

Tongyang Li, Xinzhao Wang, Yexin Zhang

Computing Nash equilibria of zero-sum games in classical and quantum settings is extensively studied. For general-sum games, computing Nash equilibria is PPAD-hard and the computing of a more general concept called correlated equilibria has been widely explored in game theory. In this paper, we initiate the study of quantum algorithms for computing $\varepsilon$-approximate correlated equilibria (CE) and coarse correlated equilibria (CCE) in multi-player normal-form games. Our approach utilizes quantum improvements to the multi-scale Multiplicative Weight Update (MWU) method for CE calculations, achieving a query complexity of $\tilde{O}(m\sqrt{n})$ for fixed $\varepsilon$. For CCE, we extend techniques from quantum algorithms for zero-sum games to multi-player settings, achieving query complexity $\tilde{O}(m\sqrt{n}/\varepsilon^{2.5})$. Both algorithms demonstrate a near-optimal scaling in the number of players $m$ and actions $n$, as confirmed by our quantum query lower bounds.

arXiv:2510.16782•neural information processing systems•Jan 1, 2025•0 citations

Projected Variational Quantum Extragradient for Zero-Sum Games

Duong The Do, Matthew Aldridge, Duong Tung Nguyen

We propose a projected variational quantum extragradient framework for computing approximate Nash equilibria in two-player zero-sum matrix games. Mixed strategies are parameterized as Born distributions of parameterized quantum circuits, transforming the classical bilinear saddle-point problem into a smooth but generally nonconvex-nonconcave problem in circuit-parameter space. To support arbitrary game sizes, we introduce a dominated embedding that maps$({m},{n})$games to qubit-compatible power-of-two dimensions while preserving equilibrium structure. We develop a projected extragradient method using parameter-shift gradient estimators and establish variance bounds scaling as${O}({1}/{S})$with the number of measurement shots$S$, together with convergence to approximate first-order stationarity under standard assumptions. Since stationarity does not necessarily imply equilibrium optimality, performance is evaluated using the game-space Nash gap. Numerical results show high-precision equilibrium computation on structured instances up to${32} \times {32}$, while highlighting challenges in unstructured settings.

arXiv:2604.16466•IEEE Control Systems Letters•Jan 1, 2026•0 citations

A four-player potential game for barren-plateau-aware quantum ansatz design

Rubén Darío Guerrero

We cast the design of parameterized quantum circuits as a four-player potential game whose state is a circuit directed acyclic graph (DAG) and whose players encode trainability, non-stabilizerness, task performance, and hardware cost. Per-player restricted action sets factorize the move space into append, remove, retype, and rewire operations; a block-coordinate $\varepsilon$-Nash residual $δ_\text{Nash}$ certifies that no single player can improve unilaterally. A single weight sweep on MaxCut $K_4$ traces a Pareto frontier from a Clifford endpoint $(M_2/n,\langle H\rangle)=(0,4.00)$ to a non-Clifford endpoint $(0.48,3.30)$. On three four-qubit hardware topologies (heavy-hex, $2\times 2$ grid, Rydberg all-to-all), Nash search achieves the highest mean potential; on the $2\times 2$ grid Nash reaches the theoretical ceiling $Φ_\text{max}=4.10$ on two of five seeds while the simulated-annealing baseline does so on one; paired Wilcoxon tests over five seeds cannot reject the null on any single topology ($p\ge 0.22$). On LiH/STO-3G, seeding Nash from a 58-gate Givens-doubles ansatz produces a 48-operation, depth-25 circuit retaining $97.7\%$ of the correlation energy while simultaneously reducing gate count, increasing non-stabilizerness, and controlling trainability. The framework is complementary to energy-only searches such as ADAPT-VQE and k-UpCCGSD, which reach chemical accuracy with fewer operations but do not optimize the other three axes.

quant-pharXiv:2604.21955•Apr 24, 2026•0 citations
Strategic decision-making among many agents under incomplete information is central to economics, security, and multi-agent artificial intelligence (AI). Computing equilibria in such settings is challenging because the joint type-action space grows exponentially with the number of players. In binary-type, binary-action Bayesian games with nnn players, an explicit representation over type-action profiles requires O(22n)O(2^{2n})O(22n) entries, making direct linear-programming (LP) formulations increasingly costly as nnn grows. We propose a hybrid quantum-classical framework for approximating Bayes correlated equilibrium (BCE) using a parameterized quantum circuit (PQC). The PQC represents the conditional distribution over joint actions using O(nL)O(nL)O(nL) trainable parameters, where LLL denotes the circuit depth; for the largest trained setting, n=8n=8n=8 and L=2L=2L=2, this corresponds to 484848 trainable angles. Each player count is trained independently by maximizing expected social welfare with a penalty on positive aggregated BCE obedience violations. On a strategically coupled Bayesian congestion game with n=2,4,6,8n=2,4,6,8n=2,4,6,8 players, feasible PQC solutions attain higher welfare than MCCFR and DCFR product-strategy baselines while satisfying εmax⁡≤10−3ε_{\max}\leq10^{-3}εmax​≤10−3, where εmax⁡ε_{\max}εmax​ denotes the maximum positive aggregated BCE obedience violation. Across five independent runs per setting, all runs are feasible for n=2,4,6n=2,4,6n=2,4,6, while four of five are feasible for n=8n=8n=8. PQC welfare remains below the exact LP optimum, with the absolute gap increasing with nnn, while classical state-vector simulation prevents PQC training beyond eight players. These results demonstrate the use of a compact PQC parameterization for approximate equilibrium computation and quantify its welfare, feasibility, and classical simulation scaling on the studied benchmark.
Abstract We demonstrate a Bayesian quantum game on an ion-trap quantum computer with five qubits. The players share an entangled pair of qubits and perform rotations on their qubit as the strategy choice. Two five-qubit circuits are sufficient to run all 16 possible strategy choice sets in a game with four possible strategies. The data are then parsed into player types randomly in order to combine them classically into a Bayesian framework. We exhaustively compute the possible strategies of the game so that the experimental data can be used to solve for the Nash equilibria of the game directly. Then we compare the payoff at the Nash equilibria and location of discontinuous changes in the payoff obtained from the experimental data to the theory, and study how it changes as a function of the amount of entanglement.
Deep reinforcement learning (DRL) is a standard approach to sequential decision-making under uncertainty, where value functions are often approximated with deep neural networks such as Deep Q-Networks (DQNs). Parameterized quantum circuits (PQCs) have emerged as a flexible modeling primitive for near-term quantum hardware, enabling hybrid quantum–classical predictors in which a PQC produces bounded expectation-value features that are processed by classical layers. A practical limitation of many quantum learning approaches, however, is the need for quantum hardware not only during training but also at deployment time. In this work, we study PQC-driven value-based agents in the CartPole control benchmark. Using a common DQN-style training loop, we compare classical DQN baselines, a PQC-based Q-network, and a hybrid workflow that leverages classical shadows for evaluation-only deployment. To probe near-term practicality, we further examine robustness by injecting additive Gaussian perturbations into the quantum feature vector across multiple noise amplitudes.
Quantum games with incomplete information can be studied within a Bayesian framework. We analyze games quantized within the EWL framework [Eisert, Wilkens, and Lewenstein, Phys Rev. Lett. 83, 3077 (1999)]. We solve for the Nash equilibria of a variety of two-player quantum games and compare the results to the solutions of the corresponding classical games. We then analyze Bayesian games where there is uncertainty about the player types in two-player conflicting interest games. The solutions to the Bayesian games are found to have a phase diagram-like structure where different equilibria exist in different parameter regions, depending both on the amount of uncertainty and the degree of entanglement. We find that in games where a Pareto-optimal solution is not a Nash equilibrium, it is possible for the quantized game to have an advantage over the classical version. In addition, we analyze the behavior of the solutions as the strategy choices approach an unrestricted operation. We find that some games have a continuum of solutions, bounded by the solutions of a simpler restricted game. A deeper understanding of Bayesian quantum game theory could lead to novel quantum applications in a multi-agent setting.
Computing Nash equilibria of zero-sum games in classical and quantum settings is extensively studied. For general-sum games, computing Nash equilibria is PPAD-hard and the computing of a more general concept called correlated equilibria has been widely explored in game theory. In this paper, we initiate the study of quantum algorithms for computing ε\varepsilonε-approximate correlated equilibria (CE) and coarse correlated equilibria (CCE) in multi-player normal-form games. Our approach utilizes quantum improvements to the multi-scale Multiplicative Weight Update (MWU) method for CE calculations, achieving a query complexity of O~(mn)\tilde{O}(m\sqrt{n})O~(mn​) for fixed ε\varepsilonε. For CCE, we extend techniques from quantum algorithms for zero-sum games to multi-player settings, achieving query complexity O~(mn/ε2.5)\tilde{O}(m\sqrt{n}/\varepsilon^{2.5})O~(mn​/ε2.5). Both algorithms demonstrate a near-optimal scaling in the number of players mmm and actions nnn, as confirmed by our quantum query lower bounds.
We propose a projected variational quantum extragradient framework for computing approximate Nash equilibria in two-player zero-sum matrix games. Mixed strategies are parameterized as Born distributions of parameterized quantum circuits, transforming the classical bilinear saddle-point problem into a smooth but generally nonconvex-nonconcave problem in circuit-parameter space. To support arbitrary game sizes, we introduce a dominated embedding that maps(m,n)({m},{n})(m,n)games to qubit-compatible power-of-two dimensions while preserving equilibrium structure. We develop a projected extragradient method using parameter-shift gradient estimators and establish variance bounds scaling asO(1/S){O}({1}/{S})O(1/S)with the number of measurement shotsSSS, together with convergence to approximate first-order stationarity under standard assumptions. Since stationarity does not necessarily imply equilibrium optimality, performance is evaluated using the game-space Nash gap. Numerical results show high-precision equilibrium computation on structured instances up to32×32{32} \times {32}32×32, while highlighting challenges in unstructured settings.
We cast the design of parameterized quantum circuits as a four-player potential game whose state is a circuit directed acyclic graph (DAG) and whose players encode trainability, non-stabilizerness, task performance, and hardware cost. Per-player restricted action sets factorize the move space into append, remove, retype, and rewire operations; a block-coordinate ε\varepsilonε-Nash residual δNashδ_\text{Nash}δNash​ certifies that no single player can improve unilaterally. A single weight sweep on MaxCut K4K_4K4​ traces a Pareto frontier from a Clifford endpoint (M2/n,⟨H⟩)=(0,4.00)(M_2/n,\langle H\rangle)=(0,4.00)(M2​/n,⟨H⟩)=(0,4.00) to a non-Clifford endpoint (0.48,3.30)(0.48,3.30)(0.48,3.30). On three four-qubit hardware topologies (heavy-hex, 2×22\times 22×2 grid, Rydberg all-to-all), Nash search achieves the highest mean potential; on the 2×22\times 22×2 grid Nash reaches the theoretical ceiling Φmax=4.10Φ_\text{max}=4.10Φmax​=4.10 on two of five seeds while the simulated-annealing baseline does so on one; paired Wilcoxon tests over five seeds cannot reject the null on any single topology (p≥0.22p\ge 0.22p≥0.22). On LiH/STO-3G, seeding Nash from a 58-gate Givens-doubles ansatz produces a 48-operation, depth-25 circuit retaining 97.7%97.7\%97.7% of the correlation energy while simultaneously reducing gate count, increasing non-stabilizerness, and controlling trainability. The framework is complementary to energy-only searches such as ADAPT-VQE and k-UpCCGSD, which reach chemical accuracy with fewer operations but do not optimize the other three axes.