{"title":"量子规则系统的自动进化设计及其在量子强化学习中的应用","authors":"Manuel P. Cuéllar, M. C. Pegalajar, C. Cano","doi":"10.1007/s11128-024-04391-0","DOIUrl":null,"url":null,"abstract":"<p>Explainable artificial intelligence is a research topic whose relevance has increased in recent years, especially with the advent of large machine learning models. However, very few attempts have been proposed to improve interpretability in the case of quantum artificial intelligence, and many existing quantum machine learning models in the literature can be considered almost as black boxes. In this article, we argue that an appropriate semantic interpretation of a given quantum circuit that solves a problem can be of interest to the user not only to certify the correct behavior of the learned model, but also to obtain a deeper insight into the problem at hand and its solution. We focus on decision-making problems that can be formulated as classification tasks and propose a method for learning quantum rule-based systems to solve them using evolutionary optimization algorithms. The approach is tested to learn rules that solve control and decision-making tasks in reinforcement learning environments, to provide interpretable agent policies that help to understand the internal dynamics of an unknown environment. Our results conclude that the learned policies are not only highly explainable, but can also help detect non-relevant features of problems and produce a minimal set of rules.</p>","PeriodicalId":746,"journal":{"name":"Quantum Information Processing","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Automatic evolutionary design of quantum rule-based systems and applications to quantum reinforcement learning\",\"authors\":\"Manuel P. Cuéllar, M. C. Pegalajar, C. Cano\",\"doi\":\"10.1007/s11128-024-04391-0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Explainable artificial intelligence is a research topic whose relevance has increased in recent years, especially with the advent of large machine learning models. However, very few attempts have been proposed to improve interpretability in the case of quantum artificial intelligence, and many existing quantum machine learning models in the literature can be considered almost as black boxes. In this article, we argue that an appropriate semantic interpretation of a given quantum circuit that solves a problem can be of interest to the user not only to certify the correct behavior of the learned model, but also to obtain a deeper insight into the problem at hand and its solution. We focus on decision-making problems that can be formulated as classification tasks and propose a method for learning quantum rule-based systems to solve them using evolutionary optimization algorithms. The approach is tested to learn rules that solve control and decision-making tasks in reinforcement learning environments, to provide interpretable agent policies that help to understand the internal dynamics of an unknown environment. Our results conclude that the learned policies are not only highly explainable, but can also help detect non-relevant features of problems and produce a minimal set of rules.</p>\",\"PeriodicalId\":746,\"journal\":{\"name\":\"Quantum Information Processing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.2000,\"publicationDate\":\"2024-05-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Quantum Information Processing\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1007/s11128-024-04391-0\",\"RegionNum\":3,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PHYSICS, MATHEMATICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Quantum Information Processing","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1007/s11128-024-04391-0","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PHYSICS, MATHEMATICAL","Score":null,"Total":0}
Automatic evolutionary design of quantum rule-based systems and applications to quantum reinforcement learning
Explainable artificial intelligence is a research topic whose relevance has increased in recent years, especially with the advent of large machine learning models. However, very few attempts have been proposed to improve interpretability in the case of quantum artificial intelligence, and many existing quantum machine learning models in the literature can be considered almost as black boxes. In this article, we argue that an appropriate semantic interpretation of a given quantum circuit that solves a problem can be of interest to the user not only to certify the correct behavior of the learned model, but also to obtain a deeper insight into the problem at hand and its solution. We focus on decision-making problems that can be formulated as classification tasks and propose a method for learning quantum rule-based systems to solve them using evolutionary optimization algorithms. The approach is tested to learn rules that solve control and decision-making tasks in reinforcement learning environments, to provide interpretable agent policies that help to understand the internal dynamics of an unknown environment. Our results conclude that the learned policies are not only highly explainable, but can also help detect non-relevant features of problems and produce a minimal set of rules.
期刊介绍:
Quantum Information Processing is a high-impact, international journal publishing cutting-edge experimental and theoretical research in all areas of Quantum Information Science. Topics of interest include quantum cryptography and communications, entanglement and discord, quantum algorithms, quantum error correction and fault tolerance, quantum computer science, quantum imaging and sensing, and experimental platforms for quantum information. Quantum Information Processing supports and inspires research by providing a comprehensive peer review process, and broadcasting high quality results in a range of formats. These include original papers, letters, broadly focused perspectives, comprehensive review articles, book reviews, and special topical issues. The journal is particularly interested in papers detailing and demonstrating quantum information protocols for cryptography, communications, computation, and sensing.