Quantum entanglement provides a competitive advantage in adversarial games

TL;DR

This study demonstrates that quantum entanglement enhances the performance of quantum-classical hybrid agents in competitive reinforcement learning tasks like Pong, outperforming separable circuits and classical models.

Contribution

It provides the first controlled comparison showing entanglement's role in improving representation learning in competitive RL environments.

Findings

Entangled circuits outperform separable ones with similar parameters.

Entangled circuits match or surpass classical neural networks in low-capacity regimes.

Representation analysis shows entanglement leads to structurally distinct features.

Abstract

Whether uniquely quantum resources confer advantages in fully classical, competitive environments remains an open question. Competitive zero-sum reinforcement learning is particularly challenging, as success requires modelling dynamic interactions between opposing agents rather than static state-action mappings. Here, we conduct a controlled study isolating the role of quantum entanglement in a quantum-classical hybrid agent trained on Pong, a competitive Markov game. An 8-qubit parameterised quantum circuit serves as a feature extractor within a proximal policy optimisation framework, allowing direct comparison between separable circuits and architectures incorporating fixed (CZ) or trainable (IsingZZ) entangling gates. Entangled circuits consistently outperform separable counterparts with comparable parameter counts and, in low-capacity regimes, match or exceed classical multilayer perceptron baselines. Representation similarity analysis further shows that entangled circuits learn structurally distinct features, consistent with improved modelling of interacting state variables. These findings establish entanglement as a function resource for representation learning in competitive reinforcement learning.