Talk · Communications in computer and information science · October 23, 2026
Explainable Variational Quantum Policy Gradient: SHAP-Based Interpretability of Quantum Reinforcement Learning Agents on CartPole
Sandeep Gupta, Sazzad Hossain, Akmal Akhatov, Mekhriddin Nurmamatov, Kanad Ray
Abstract
The decisions of variational quantum reinforcement learning agents remain largely opaque, limiting trust in safety-critical deployments. We present the first application of SHapley Additive exPlanations (SHAP) to a Variational Quantum Policy Gradient (VQPG) agent trained on CartPole-v1. Our 4-qubit hybrid quantum-classical policy uses only 46 trainable parameters and achieves a mean evaluation score of $$496.4 \pm 8.1$$ over ten independent seeds (maximum 500.0), compared to $$249.7 \pm 38.6$$ for a standard Deep Q-Network (DQN) with 9 220 parameters and $$412.3 \pm 67.9$$ for a parameter-matched Tiny-MLP (30 parameters, identical training budget). SHAP analysis identifies Pole Angular Velocity as the dominant decision feature (mean $$|\phi | = 0.2859$$ , approximately $$7\times $$ the next feature), consistent with classical control theory for inverted pendulum stabilisation. This attribution is stable across five independently sampled background sets (coefficient of variation $$3.1\%$$ ), confirming the reliability of the explanation. We emphasise that all results are obtained under noiseless simulation; no claim of quantum advantage in the complexity-theoretic sense is made. The complete experimental package is deposited on https://zenodo.org/ under CC-BY 4.0.
More by Mekhriddin Nurmamatov
- Lean Quantum Intelligence: A Compact Variational-Circuit Hybrid for Turbofan RUL Prediction with SHAP AttributionComputers · 2026
- Investigation of Vulnerabilities of Machine Learning Models to Adversarial Attacks in Smart Grid Forecasting SystemsAdvances in computational intelligence and robotics book series · 2026
- Capacity-Constrained Multi-robot Task Allocation via Quantum Approximate Optimisation: A Reproducible Benchmark on a Solomon VRPTW C101-Derived InstanceCommunications in computer and information science · 2026
- Forecasting Electrical Load and Renewable Energy Generation Using Machine Learning MethodsAdvances in computational intelligence and robotics book series · 2026