Efficient Dimensionality Reduction Strategies for Quantum Reinforcement Learning
Quantum neural networks constitute one of the most promising applications of Quantum Machine Learning, as they leverage both the capabilities of classical neural networks and the unique advantages of quantum mechanics. Moreover, quantum mechanics has demonstrated its ability to detect atypical patte...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10258300/ |
| _version_ | 1797668022721183744 |
|---|---|
| author | Eva Andres M. P. Cuellar G. Navarro |
| author_facet | Eva Andres M. P. Cuellar G. Navarro |
| author_sort | Eva Andres |
| collection | DOAJ |
| description | Quantum neural networks constitute one of the most promising applications of Quantum Machine Learning, as they leverage both the capabilities of classical neural networks and the unique advantages of quantum mechanics. Moreover, quantum mechanics has demonstrated its ability to detect atypical patterns in data that are challenging for classical approaches to recognize. However, despite their potential, there are still open questions such as barren plateau phenomenon and the challenges of scalability and the curse of dimensionality, which become particularly relevant in Reinforcement Learning (RL) when working in environments with high-dimensional state and action spaces. This study delves into the critical realm of representing classical data as quantum states, a topic of keen interest across the scientific community. The aim is to construct streamlined circuits for efficient execution on quantum computers and simulators using minimal qubits and entanglement gates to evade barren plateau phenomena and reducing computational times. Our investigation examines and validates the efficacy of three strategies for data management and dimensionality reduction in real-world, large-scale environments for Quantum Reinforcement Learning, particularly in energy efficiency scenarios. The techniques encompass amplitude encoding, linear layer preprocessing, and data reuploading, supplemented by trainable parameters. This research sheds light on the potential of quantum machine learning in enhancing real-world environments, including energy efficiency scenarios and showcases the capabilities of quantum neural networks in the reinforcement learning landscape. |
| first_indexed | 2024-03-11T20:22:03Z |
| format | Article |
| id | doaj.art-1cc46b14ae564a43bb2539293cb9ea3a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T20:22:03Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1cc46b14ae564a43bb2539293cb9ea3a2023-10-02T23:01:31ZengIEEEIEEE Access2169-35362023-01-011110453410455310.1109/ACCESS.2023.331817310258300Efficient Dimensionality Reduction Strategies for Quantum Reinforcement LearningEva Andres0https://orcid.org/0000-0002-9451-340XM. P. Cuellar1https://orcid.org/0000-0002-9736-1608G. Navarro2https://orcid.org/0000-0002-9895-5686Department of Computer Science and Artificial Intelligence, University of Granada, Granada, SpainDepartment of Computer Science and Artificial Intelligence, University of Granada, Granada, SpainDepartment of Computer Science and Artificial Intelligence, University of Granada, Granada, SpainQuantum neural networks constitute one of the most promising applications of Quantum Machine Learning, as they leverage both the capabilities of classical neural networks and the unique advantages of quantum mechanics. Moreover, quantum mechanics has demonstrated its ability to detect atypical patterns in data that are challenging for classical approaches to recognize. However, despite their potential, there are still open questions such as barren plateau phenomenon and the challenges of scalability and the curse of dimensionality, which become particularly relevant in Reinforcement Learning (RL) when working in environments with high-dimensional state and action spaces. This study delves into the critical realm of representing classical data as quantum states, a topic of keen interest across the scientific community. The aim is to construct streamlined circuits for efficient execution on quantum computers and simulators using minimal qubits and entanglement gates to evade barren plateau phenomena and reducing computational times. Our investigation examines and validates the efficacy of three strategies for data management and dimensionality reduction in real-world, large-scale environments for Quantum Reinforcement Learning, particularly in energy efficiency scenarios. The techniques encompass amplitude encoding, linear layer preprocessing, and data reuploading, supplemented by trainable parameters. This research sheds light on the potential of quantum machine learning in enhancing real-world environments, including energy efficiency scenarios and showcases the capabilities of quantum neural networks in the reinforcement learning landscape.https://ieeexplore.ieee.org/document/10258300/Energy efficiencyquantum neural networksquantum encodingquantum reinforcement learningvariational quantum circuits |
| spellingShingle | Eva Andres M. P. Cuellar G. Navarro Efficient Dimensionality Reduction Strategies for Quantum Reinforcement Learning IEEE Access Energy efficiency quantum neural networks quantum encoding quantum reinforcement learning variational quantum circuits |
| title | Efficient Dimensionality Reduction Strategies for Quantum Reinforcement Learning |
| title_full | Efficient Dimensionality Reduction Strategies for Quantum Reinforcement Learning |
| title_fullStr | Efficient Dimensionality Reduction Strategies for Quantum Reinforcement Learning |
| title_full_unstemmed | Efficient Dimensionality Reduction Strategies for Quantum Reinforcement Learning |
| title_short | Efficient Dimensionality Reduction Strategies for Quantum Reinforcement Learning |
| title_sort | efficient dimensionality reduction strategies for quantum reinforcement learning |
| topic | Energy efficiency quantum neural networks quantum encoding quantum reinforcement learning variational quantum circuits |
| url | https://ieeexplore.ieee.org/document/10258300/ |
| work_keys_str_mv | AT evaandres efficientdimensionalityreductionstrategiesforquantumreinforcementlearning AT mpcuellar efficientdimensionalityreductionstrategiesforquantumreinforcementlearning AT gnavarro efficientdimensionalityreductionstrategiesforquantumreinforcementlearning |