{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T03:47:51Z","timestamp":1775274471639,"version":"3.50.1"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030041663","type":"print"},{"value":"9783030041670","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-04167-0_32","type":"book-chapter","created":{"date-parts":[[2018,11,16]],"date-time":"2018-11-16T18:47:46Z","timestamp":1542394066000},"page":"350-361","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Feature Learning and Transfer Performance Prediction for Video Reinforcement Learning Tasks via a Siamese Convolutional Neural Network"],"prefix":"10.1007","author":[{"given":"Jinhua","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,11,17]]},"reference":[{"key":"32_CR1","unstructured":"Ammar, H.B., et al.: An automated measure of MDP similarity for transfer in reinforcement learning. In: Workshop at the 28th AAAI Conference on Artificial Intelligence (2014)"},{"key":"32_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1007\/978-3-642-35289-8_26","volume-title":"Neural Networks: Tricks of the Trade","author":"Y Bengio","year":"2012","unstructured":"Bengio, Y.: Practical recommendations for gradient-based training of deep architectures. In: Montavon, G., Orr, G.B., M\u00fcller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 437\u2013478. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-35289-8_26"},{"key":"32_CR3","unstructured":"Fitzgerald, T., Goel, A., Thomaz, A.: Human-robot co-creativity: task transfer on a spectrum of similarity. In: Proceedings of 8th International Conference on Computational Creativity (2017)"},{"key":"32_CR4","unstructured":"Frank, E., Hall, M.A., Witten, I.H.: The WEKA workbench. In: Online Appendix for \u201cData Mining: Practical Machine Learning Tools and Techniques\u201d, 4th edn. Morgan Kaufmann, Los Altos (2016)"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Hanna, J.P., Stone, P.: Grounded action transformation for robot learning in simulation. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence, pp. 3834\u20133840. AAAI Press (2017)","DOI":"10.1609\/aaai.v31i1.11124"},{"key":"32_CR6","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. CoRR abs\/1412.6980 (2014)"},{"issue":"1","key":"32_CR7","first-page":"1333","volume":"13","author":"G Konidaris","year":"2012","unstructured":"Konidaris, G., Scheidwasser, I., Barto, A.G.: Transfer in reinforcement learning via shared features. J. Mach. Learn. Res. 13(1), 1333\u20131371 (2012)","journal-title":"J. Mach. Learn. Res."},{"key":"32_CR8","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1106\u20131114 (2012)"},{"key":"32_CR9","series-title":"Adaptation, Learning, and Optimization","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-642-27645-3_5","volume-title":"Reinforcement Learning: State-of-the-Art","author":"A Lazaric","year":"2012","unstructured":"Lazaric, A.: Transfer in reinforcement learning: a framework and a survey. In: Wiering, M., van Otterlo, M. (eds.) Reinforcement Learning: State-of-the-Art. Adaptation, Learning, and Optimization, vol. 12, pp. 143\u2013173. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3_5"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Lazaric, A., Restelli, M., Bonarini, A.: Transfer of samples in batch reinforcement learning. In: Proceedings of the 25th International Conference on Machine Learning, pp. 544\u2013551. ACM (2008)","DOI":"10.1145\/1390156.1390225"},{"issue":"7553","key":"32_CR11","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Lecun","year":"2015","unstructured":"Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"issue":"3","key":"32_CR12","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/s10994-008-5061-y","volume":"73","author":"N Mehta","year":"2008","unstructured":"Mehta, N., Natarajan, S., Tadepalli, P., Fern, A.: Transfer in variable-reward hierarchical reinforcement learning. Mach. Learn. 73(3), 289\u2013312 (2008)","journal-title":"Mach. Learn."},{"key":"32_CR13","doi-asserted-by":"publisher","first-page":"428567","DOI":"10.1155\/2014\/428567","volume":"2014","author":"A Mousavi","year":"2014","unstructured":"Mousavi, A., Araabi, B.N., Ahmadabadi, M.N.: Context transfer in reinforcement learning using action-value functions. Comput. Intell. Neurosci. 2014, 428567 (2014)","journal-title":"Comput. Intell. Neurosci."},{"key":"32_CR14","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.neucom.2013.04.045","volume":"137","author":"J Pan","year":"2014","unstructured":"Pan, J., Wang, X., Cheng, Y., Cao, G.: Multi-source transfer ELM-based Q learning. Neurocomputing 137, 57\u201364 (2014)","journal-title":"Neurocomputing"},{"key":"32_CR15","unstructured":"Rosenstein, M.T., Marx, Z., Kaelbling, L.P., Dietterich, T.G.: To transfer or not to transfer. In: NIPS Workshop on Inductive Transfer: 10 Years Later (2005)"},{"key":"32_CR16","unstructured":"Rummery, G.A., Niranjan, M.: On-line q-learning using connectionist systems. Technical report, University of Cambridge (1994)"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Sinapov, J., Narvekar, S., Leonetti, M., Stone, P.: Learning inter-task transferability in the absence of target task samples. In: Proceedings of the 14th International Conference on Autonomous Agents and Multiagent Systems, pp. 725\u2013733. ACM (2015)","DOI":"10.65109\/XMCC3729"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Song, J., Gao, Y., Wang, H., An, B.: Measuring the distance between finite Markov decision processes. In: Proceedings of the 15th International Conference on Autonomous Agents and Multiagent Systems, pp. 468\u2013476. ACM (2016)","DOI":"10.65109\/HCGU8533"},{"issue":"1","key":"32_CR19","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1080\/09540091.2014.885279","volume":"26","author":"ME Taylor","year":"2014","unstructured":"Taylor, M.E., Carboni, N., Fachantidis, A., Vlahavas, I.P., Torrey, L.: Reinforcement learning agents providing advice in complex video games. Connect. Sci. 26(1), 45\u201363 (2014)","journal-title":"Connect. Sci."},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Taylor, M.E., Stone, P.: Behavior transfer for value-function-based reinforcement learning. In: Proceedings of the 4th International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 53\u201359. ACM (2005)","DOI":"10.1145\/1082473.1082482"},{"key":"32_CR21","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res. 10, 1633\u20131685 (2009)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"32_CR22","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1609\/aimag.v32i1.2329","volume":"32","author":"ME Taylor","year":"2011","unstructured":"Taylor, M.E., Stone, P.: An introduction to intertask transfer for reinforcement learning. AI Mag. 32(1), 15 (2011)","journal-title":"AI Mag."},{"issue":"3\u20134","key":"32_CR23","first-page":"279","volume":"8","author":"C Watkins","year":"1992","unstructured":"Watkins, C., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"32_CR24","unstructured":"Wikipedia: Ms. PacMan (2018). https:\/\/en.wikipedia.org\/wiki\/Ms._Pac-Man"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-04167-0_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T02:53:20Z","timestamp":1775271200000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-04167-0_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030041663","9783030041670"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-04167-0_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"17 November 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Siem Reap","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambodia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conference.cs.cityu.edu.hk\/iconip\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"575","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"401","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"70% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}