Pub Date : 2021-01-01Epub Date: 2021-08-02DOI: 10.1007/s42484-021-00049-7
A Hamann, V Dunjko, S Wölk
In recent years, quantum-enhanced machine learning has emerged as a particularly fruitful application of quantum algorithms, covering aspects of supervised, unsupervised and reinforcement learning. Reinforcement learning offers numerous options of how quantum theory can be applied, and is arguably the least explored, from a quantum perspective. Here, an agent explores an environment and tries to find a behavior optimizing some figure of merit. Some of the first approaches investigated settings where this exploration can be sped-up, by considering quantum analogs of classical environments, which can then be queried in superposition. If the environments have a strict periodic structure in time (i.e. are strictly episodic), such environments can be effectively converted to conventional oracles encountered in quantum information. However, in general environments, we obtain scenarios that generalize standard oracle tasks. In this work, we consider one such generalization, where the environment is not strictly episodic, which is mapped to an oracle identification setting with a changing oracle. We analyze this case and show that standard amplitude-amplification techniques can, with minor modifications, still be applied to achieve quadratic speed-ups. In addition, we prove that an algorithm based on Grover iterations is optimal for oracle identification even if the oracle changes over time in a way that the "rewarded space" is monotonically increasing. This result constitutes one of the first generalizations of quantum-accessible reinforcement learning.
{"title":"Quantum-accessible reinforcement learning beyond strictly epochal environments.","authors":"A Hamann, V Dunjko, S Wölk","doi":"10.1007/s42484-021-00049-7","DOIUrl":"https://doi.org/10.1007/s42484-021-00049-7","url":null,"abstract":"<p><p>In recent years, quantum-enhanced machine learning has emerged as a particularly fruitful application of quantum algorithms, covering aspects of supervised, unsupervised and reinforcement learning. Reinforcement learning offers numerous options of how quantum theory can be applied, and is arguably the least explored, from a quantum perspective. Here, an agent explores an environment and tries to find a behavior optimizing some figure of merit. Some of the first approaches investigated settings where this exploration can be sped-up, by considering quantum analogs of classical environments, which can then be queried in superposition. If the environments have a strict periodic structure in time (i.e. are strictly episodic), such environments can be effectively converted to conventional oracles encountered in quantum information. However, in general environments, we obtain scenarios that generalize standard oracle tasks. In this work, we consider one such generalization, where the environment is not strictly episodic, which is mapped to an oracle identification setting with a changing oracle. We analyze this case and show that standard amplitude-amplification techniques can, with minor modifications, still be applied to achieve quadratic speed-ups. In addition, we prove that an algorithm based on Grover iterations is optimal for oracle identification even if the oracle changes over time in a way that the \"rewarded space\" is monotonically increasing. This result constitutes one of the first generalizations of quantum-accessible reinforcement learning.</p>","PeriodicalId":29924,"journal":{"name":"Quantum Machine Intelligence","volume":"3 2","pages":"22"},"PeriodicalIF":4.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8550166/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39669146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-07DOI: 10.1007/s42484-023-00097-1
K. Meichanetzidis, Alexis Toumi, Giovanni de Felice, B. Coecke
{"title":"Grammar-aware sentence classification on quantum computers","authors":"K. Meichanetzidis, Alexis Toumi, Giovanni de Felice, B. Coecke","doi":"10.1007/s42484-023-00097-1","DOIUrl":"https://doi.org/10.1007/s42484-023-00097-1","url":null,"abstract":"","PeriodicalId":29924,"journal":{"name":"Quantum Machine Intelligence","volume":"5 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2020-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46661142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-16DOI: 10.1007/s42484-020-00028-4
C. Silva, A. Aguiar, P. Lima, I. Dutra
{"title":"Mapping graph coloring to quantum annealing","authors":"C. Silva, A. Aguiar, P. Lima, I. Dutra","doi":"10.1007/s42484-020-00028-4","DOIUrl":"https://doi.org/10.1007/s42484-020-00028-4","url":null,"abstract":"","PeriodicalId":29924,"journal":{"name":"Quantum Machine Intelligence","volume":" ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1007/s42484-020-00028-4","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42441517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-19DOI: 10.1007/s42484-021-00042-0
S. Yarkoni, A. Kleshchonok, Yury Dzerin, F. Neukart, M. Hilbert
{"title":"Semi-supervised time series classification method for quantum computing","authors":"S. Yarkoni, A. Kleshchonok, Yury Dzerin, F. Neukart, M. Hilbert","doi":"10.1007/s42484-021-00042-0","DOIUrl":"https://doi.org/10.1007/s42484-021-00042-0","url":null,"abstract":"","PeriodicalId":29924,"journal":{"name":"Quantum Machine Intelligence","volume":"3 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1007/s42484-021-00042-0","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41737862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-13DOI: 10.1007/s42484-020-00026-6
E. Jones, P. Graf, E. Kapit, W. Jones
{"title":"K-spin Hamiltonian for quantum-resolvable Markov decision processes","authors":"E. Jones, P. Graf, E. Kapit, W. Jones","doi":"10.1007/s42484-020-00026-6","DOIUrl":"https://doi.org/10.1007/s42484-020-00026-6","url":null,"abstract":"","PeriodicalId":29924,"journal":{"name":"Quantum Machine Intelligence","volume":" ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2020-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1007/s42484-020-00026-6","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49065757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号