{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T02:40:09Z","timestamp":1747190409829,"version":"3.40.5"},"reference-count":23,"publisher":"Wiley","license":[{"start":{"date-parts":[[2020,12,16]],"date-time":"2020-12-16T00:00:00Z","timestamp":1608076800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2020,12,16]]},"abstract":"<jats:p>Previous studies have shown that training a reinforcement model for the sorting problem takes very long time, even for small sets of data. To study whether transfer learning could improve the training process of reinforcement learning, we employ Q-learning as the base of the reinforcement learning algorithm, apply the sorting problem as a case study, and assess the performance from two aspects, the time expense and the brain capacity. We compare the total number of training steps between nontransfer and transfer methods to study the efficiencies and evaluate their differences in brain capacity (i.e., the percentage of the updated Q-values in the Q-table). According to our experimental results, the difference in the total number of training steps will become smaller when the size of the numbers to be sorted increases. Our results also show that the brain capacities of transfer and nontransfer reinforcement learning will be similar when they both reach a similar training level.<\/jats:p>","DOI":"10.1155\/2020\/8873057","type":"journal-article","created":{"date-parts":[[2020,12,17]],"date-time":"2020-12-17T01:09:57Z","timestamp":1608167397000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["An Empirical Investigation of Transfer Effects for Reinforcement Learning"],"prefix":"10.1155","volume":"2020","author":[{"given":"Jung-Sing","family":"Jwo","sequence":"first","affiliation":[{"name":"Master Program of Digital Innovation, Tunghai University, Taichung 40704, Taiwan"},{"name":"Department of Computer Science, Tunghai University, Taichung 40704, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6172-8201","authenticated-orcid":true,"given":"Ching-Sheng","family":"Lin","sequence":"additional","affiliation":[{"name":"Master Program of Digital Innovation, Tunghai University, Taichung 40704, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng-Hsiung","family":"Lee","sequence":"additional","affiliation":[{"name":"Master Program of Digital Innovation, Tunghai University, Taichung 40704, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya-Ching","family":"Lo","sequence":"additional","affiliation":[{"name":"Master Program of Digital Innovation, Tunghai University, Taichung 40704, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2881964"},{"article-title":"Variational inference for data-efficient model learning in pomdps","year":"2018","author":"S. Tschiatschek","key":"2"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3007951"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"volume-title":"On-Line Q-Learning Using Connectionist Systems","year":"1994","author":"G. A. Rummery","key":"5"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"article-title":"Generalization and regularization in DQN","year":"2018","author":"J. Farebrother","key":"8"},{"key":"9","first-page":"2613","article-title":"Double Q-learning","volume-title":"Advances in Neural Information Processing Systems","author":"H. V. Hasselt","year":"2010"},{"article-title":"Deep reinforcement learning with double q-learning","author":"H. Van Hasselt","key":"10","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2018.2867482"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500630"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975673.76"},{"key":"14","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume-title":"Advances in Neural Information Processing Systems","author":"J. Yosinski","year":"2014"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"16","first-page":"4077","article-title":"Prototypical networks for few-shot learning","volume-title":"Advances in Neural Information Processing Systems","author":"J. Snell","year":"2017"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2922438"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.3176\/proc.2020.3.02"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927542"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619634"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553422"},{"first-page":"2915","article-title":"Near optimal behavior via approximate state abstraction","author":"D. Abel","key":"22"},{"first-page":"10","article-title":"State abstractions for lifelong reinforcement learning","author":"D. Abel","key":"23"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2020\/8873057.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2020\/8873057.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2020\/8873057.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T23:04:34Z","timestamp":1670281474000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/cin\/2020\/8873057\/"}},"subtitle":[],"editor":[{"given":"Wassim","family":"Ayadi","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2020,12,16]]},"references-count":23,"alternative-id":["8873057","8873057"],"URL":"https:\/\/doi.org\/10.1155\/2020\/8873057","relation":{},"ISSN":["1687-5273","1687-5265"],"issn-type":[{"type":"electronic","value":"1687-5273"},{"type":"print","value":"1687-5265"}],"subject":[],"published":{"date-parts":[[2020,12,16]]}}}