mlsanityData to 7 Oct 2026

Benchmarking Quantum Reinforcement Learning

arXiv 2501.15893 ↗First posted 27 Jan 2025quant-ph cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Benchmarking and establishing proper statistical validation metrics for reinforcement learning (RL) remain ongoing challenges, where no consensus has been established yet. The emergence of quantum computing and its potential applications in quantum reinforcement learning (QRL) further complicate benchmarking efforts. To enable valid performance comparisons and to streamline current research in this area, we propose a novel benchmarking methodology, which is based on a statistical estimator for sample complexity and a definition of statistical outperformance. Furthermore, considering QRL, our methodology casts doubt on some previous claims regarding its superiority. We conducted experiments on a novel benchmarking environment with flexible levels of complexity. While we still identify possible advantages, our findings are more nuanced overall. We discuss the potential limitations of these results and explore their implications for empirical research on quantum advantage in QRL.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 54 of its 110 references that are in the map. First posted on arXiv 27 Jan 2025.

Builds on

54 of 110 references.

References · 54

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  4. 2016OpenAI Gymcited by 1,684
  5. 2018DeepMind Control Suitecited by 935
  6. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  7. 2017A Brief Survey of Deep Reinforcement Learningcited by 466
  8. 2020The power of quantum neural networkscited by 377
  9. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 361
  10. 2020A rigorous and robust quantum speed-up in supervised machine learningcited by 270
  11. 2024Reinforcement learningcited by 236
  12. 2018An Introduction to Deep Reinforcement Learningcited by 201
38 more
  1. 2019Variational Quantum Circuits for Deep Reinforcement Learningcited by 165
  2. 2019Benchmarking Model-Based Reinforcement Learningcited by 158
  3. 2021Tianshou: a Highly Modularized Deep Reinforcement Learning Librarycited by 139
  4. 2021URLB: Unsupervised Reinforcement Learning Benchmarkcited by 138
  5. 2024Barren Plateaus in Variational Quantum Computingcited by 130
  6. 2019Benchmarking Batch Deep Reinforcement Learning Algorithmscited by 108
  7. 2021Parametrized quantum policies for reinforcement learningcited by 87
  8. 2024Better than classical? The subtle art of benchmarking quantum machine learning modelscited by 82
  9. 2020Quantum circuit architecture search for variational quantum algorithmscited by 81
  10. 2016Quantum-enhanced machine learningcited by 79
  11. 2020Reinforcement Learning with Quantum Variational Circuitscited by 74
  12. 2021Model Complexity of Deep Learning: A Surveycited by 64
  13. 2018How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experimentscited by 56
  14. 2023Empirical Design in Reinforcement Learningcited by 54
  15. 2022A Survey on Quantum Reinforcement Learningcited by 50
  16. 2022Towards a Standardised Performance Evaluation Protocol for Cooperative MARLcited by 48
  17. 2016Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPUcited by 46
  18. 2020Evaluating the Performance of Reinforcement Learning Algorithmscited by 35
  19. 2024Quantum Convolutional Neural Networks are Effectively Classically Simulablecited by 33
  20. 2021Quantum Algorithms for Reinforcement Learning with a Generative Modelcited by 24
  21. 2022Quantum Policy Iteration via Amplitude Estimation and Grover Search -- Towards Quantum Advantage for Reinforcement Learningcited by 21
  22. 2022Quantum Policy Gradient Algorithm with Optimized Action Decodingcited by 21
  23. 2016Reinforcement Learning Using Quantum Boltzmann Machinescited by 19
  24. 2022Quantum Reinforcement Learning via Policy Iterationcited by 19
  25. 2013The Sample-Complexity of General Reinforcement Learningcited by 18
  26. 2024Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learningcited by 17
  27. 2024Position: Benchmarking is Limited in Reinforcement Learning Researchcited by 15
  28. 2022Quantum Deep Reinforcement Learning for Robot Navigation Taskscited by 14
  29. 2023Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RLcited by 13
  30. 2023GUARD: A Safe Reinforcement Learning Benchmarkcited by 13
  31. 2024VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainabilitycited by 12
  32. 2023Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regretcited by 9
  33. 2023Disentangling Hype from Practicality: On Realistically Achieving Quantum Advantagecited by 8
  34. 2024Qiskit-Torch-Module: Fast Prototyping of Quantum Neural Networkscited by 8
  35. 2023Quantum Computing Provides Exponential Regret Improvement in Episodic Reinforcement Learningcited by 6
  36. 2023Quantum Natural Policy Gradients: Towards Sample-Efficient Reinforcement Learningcited by 6
  37. 2017Free energy-based reinforcement learning using a quantum processorcited by 4
  38. 2021Towards Multi-Agent Reinforcement Learning using Quantum Boltzmann Machinescited by 4

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 6.

9 papers.

  1. 2025Learning Encodings by Maximizing State Distinguishability: Variational Quantum Error Correctioncited by 1
  2. 2025Platform-Agnostic Modular Architecture for Quantum Benchmarkingcited by 0
  3. 2025Formal Verification of Noisy Quantum Reinforcement Learning Policiescited by 0
  4. 2026Quantum entanglement provides a competitive advantage in adversarial gamescited by 0
  5. 2026Staged Hybridisation for Visual Quantum Reinforcement Learning via Knowledge Distillationcited by 0
  6. 2026Quantum vs. Classical Machine Learning: A Unified Empirical Comparisoncited by 0
  7. 2026QANTIS: Hardware-Calibrated Sequential POMDP Belief Updates on IBM Heroncited by 0
  8. 2026SQUARE: Structured Quantum Representation Adapters as Compact Quadratic Feature Maps for Frozen Language Modelscited by 0
  9. 2026A Width-Matched Comparison of Hybrid Quantum-Classical Self-Supervised Learning for Fingerprint Recognitioncited by 0