{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T03:24:17Z","timestamp":1743132257204,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030616151"},{"type":"electronic","value":"9783030616168"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","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":[[2020]]},"DOI":"10.1007\/978-3-030-61616-8_26","type":"book-chapter","created":{"date-parts":[[2020,10,16]],"date-time":"2020-10-16T23:07:42Z","timestamp":1602889662000},"page":"323-334","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GAN-Based Planning Model in Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Song","family":"Chen","sequence":"first","affiliation":[]},{"given":"Junpeng","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Xiaofang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jinjin","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Gongzheng","family":"Lu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,14]]},"reference":[{"key":"26_CR1","doi-asserted-by":"publisher","unstructured":"Adam, S., Busoniu, L., Babuska, R.: Experience replay for real-time reinforcement learning control. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 42(2), 201\u2013212 (2011). https:\/\/doi.org\/10.1109\/TSMCC.2011.2106494","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"26_CR2","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"26_CR3","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2172\u20132180 (2016)"},{"key":"26_CR4","doi-asserted-by":"publisher","unstructured":"Degris, T., Pilarski, P.M., Sutton, R.S.: Model-free reinforcement learning with continuous action in practice. In: 2012 American Control Conference (ACC), pp. 2177\u20132182. IEEE (2012). https:\/\/doi.org\/10.1109\/ACC.2012.6315022","DOI":"10.1109\/ACC.2012.6315022"},{"key":"26_CR5","doi-asserted-by":"publisher","unstructured":"Doya, K., Samejima, K., Katagiri, K.I., Kawato, M.: Multiple model-based reinforcement learning. Neural Comput. 14(6), 1347\u20131369 (2002). https:\/\/doi.org\/10.1162\/089976602753712972","DOI":"10.1162\/089976602753712972"},{"key":"26_CR6","unstructured":"Foerster, J., et al.: Stabilising experience replay for deep multi-agent reinforcement learning. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1146\u20131155. JMLR.org (2017)"},{"key":"26_CR7","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"issue":"6","key":"26_CR8","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Sig. Process. Mag. 29(6), 82\u201397 (2012). https:\/\/doi.org\/10.1109\/MSP.2012.2205597","journal-title":"IEEE Sig. Process. Mag."},{"key":"26_CR9","unstructured":"Karkus, P., Hsu, D., Lee, W.S.: QMDP-Net: deep learning for planning under partial observability. In: Advances in Neural Information Processing Systems, pp. 4694\u20134704 (2017)"},{"key":"26_CR10","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"issue":"7540","key":"26_CR11","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015). https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"26_CR12","unstructured":"Munos, R., Stepleton, T., Harutyunyan, A., Bellemare, M.: Safe and efficient off-policy reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 1054\u20131062 (2016)"},{"key":"26_CR13","doi-asserted-by":"publisher","unstructured":"Pan, Y., Zaheer, M., White, A., Patterson, A., White, M.: Organizing experience: a deeper look at replay mechanisms for sample-based planning in continuous state domains. arXiv preprint arXiv:1806.04624 (2018). https:\/\/doi.org\/10.24963\/ijcai.2018\/666","DOI":"10.24963\/ijcai.2018\/666"},{"key":"26_CR14","unstructured":"Pascanu, R., et al.: Learning model-based planning from scratch. arXiv preprint arXiv:1707.06170 (2017)"},{"key":"26_CR15","unstructured":"Racani\u00e8re, S., et al.: Imagination-augmented agents for deep reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 5690\u20135701 (2017)"},{"key":"26_CR16","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)"},{"issue":"5","key":"26_CR17","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1016\/j.neuron.2016.04.036","volume":"90","author":"MN Shadlen","year":"2016","unstructured":"Shadlen, M.N., Shohamy, D.: Decision making and sequential sampling from memory. Neuron 90(5), 927\u2013939 (2016). https:\/\/doi.org\/10.1016\/j.neuron.2016.04.036","journal-title":"Neuron"},{"key":"26_CR18","unstructured":"Silver, D., et al.: The predictron: end-to-end learning and planning. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 3191\u20133199. JMLR.org (2017)"},{"key":"26_CR19","doi-asserted-by":"publisher","unstructured":"Strehl, A.L., Li, L., Wiewiora, E., Langford, J., Littman, M.L.: PAC model-free reinforcement learning. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 881\u2013888 (2006). https:\/\/doi.org\/10.1145\/1143844.1143955","DOI":"10.1145\/1143844.1143955"},{"issue":"4","key":"26_CR20","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1145\/122344.122377","volume":"2","author":"RS Sutton","year":"1991","unstructured":"Sutton, R.S.: Dyna, an integrated architecture for learning, planning, and reacting. ACM SIGART Bull. 2(4), 160\u2013163 (1991). https:\/\/doi.org\/10.1145\/122344.122377","journal-title":"ACM SIGART Bull."},{"key":"26_CR21","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"26_CR22","volume-title":"Introduction to Reinforcement Learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G., et al.: Introduction to Reinforcement Learning, vol. 135. MIT Press, Cambridge (1998)"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Tamar, A., Wu, Y., Thomas, G., Levine, S., Abbeel, P.: Value iteration networks. In: Advances in Neural Information Processing Systems, pp. 2154\u20132162 (2016)","DOI":"10.24963\/ijcai.2017\/700"},{"key":"26_CR24","unstructured":"Wang, Z., et al.: Sample efficient actor-critic with experience replay. arXiv preprint arXiv:1611.01224 (2016)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-61616-8_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T22:05:01Z","timestamp":1619301901000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-61616-8_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030616151","9783030616168"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-61616-8_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"14 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bratislava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovakia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2020\/","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":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"249","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":"139","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":"56% - 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":"3","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":"2.5","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)"}},{"value":"*The conference was postponed to 2021 due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}