{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T10:08:03Z","timestamp":1743156483032,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030638320"},{"type":"electronic","value":"9783030638337"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/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":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-63833-7_25","type":"book-chapter","created":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T06:03:35Z","timestamp":1605765815000},"page":"295-306","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Double Replay Buffers with Restricted Gradient"],"prefix":"10.1007","author":[{"given":"Linjing","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Zongzhang","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,20]]},"reference":[{"key":"25_CR1","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. In: Advances in Neural Information Processing Systems (NIPS), pp. 5055\u20135065 (2017)"},{"key":"25_CR2","series-title":"Studies in Computational Intelligence","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11688-9","volume-title":"Interactive Collaborative Information Systems","author":"R Babu\u0161ka","year":"2010","unstructured":"Babu\u0161ka, R., Groen, F.C.: Interactive Collaborative Information Systems. SCI. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-11688-9"},{"issue":"3","key":"25_CR3","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/S0019-9958(58)80003-0","volume":"1","author":"R Bellman","year":"1958","unstructured":"Bellman, R.: Dynamic programming and stochastic control processes. Inf. Control 1(3), 228\u2013239 (1958)","journal-title":"Inf. Control"},{"key":"25_CR4","unstructured":"Brockman, G., et al.: OpenAI Gym. CoRR abs\/1606.01540 (2016). http:\/\/arxiv.org\/abs\/1606.01540"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"de Bruin, T., Kober, J., Tuyls, K., Babu\u0161ka, R.: Improved deep reinforcement learning for robotics through distribution-based experience retention. In: International Conference on Intelligent Robots and Systems (IROS), pp. 3947\u20133952. IEEE (2016)","DOI":"10.1109\/IROS.2016.7759581"},{"key":"25_CR6","unstructured":"de Bruin, T., Kober, J., Tuyls, K., Babu\u0161ka, R.: Off-policy experience retention for deep actor-critic learning. In: Deep Reinforcement Learning Workshop, Advances in Neural Information Processing Systems (NIPS) (2016)"},{"issue":"1","key":"25_CR7","first-page":"347","volume":"19","author":"T de Bruin","year":"2018","unstructured":"de Bruin, T., Kober, J., Tuyls, K., Babu\u0161ka, R.: Experience selection in deep reinforcement learning for control. J. Mach. Learn. Res. 19(1), 347\u2013402 (2018)","journal-title":"J. Mach. Learn. Res."},{"key":"25_CR8","unstructured":"De Bruin, T., Kober, J., Tuyls, K., Babu\u0161ka, R.: The importance of experience replay database composition in deep reinforcement learning. In: Deep Reinforcement Learning Workshop, Advances in Neural Information Processing Systems (NIPS) (2015)"},{"issue":"1","key":"25_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11704-018-8900-4","volume":"13","author":"TG Dietterich","year":"2019","unstructured":"Dietterich, T.G.: Robust artificial intelligence and robust human organizations. Front. Comput. Sci. 13(1), 1\u20133 (2019). https:\/\/doi.org\/10.1007\/s11704-018-8900-4","journal-title":"Front. Comput. Sci."},{"issue":"3\u20134","key":"25_CR10","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1561\/2200000071","volume":"11","author":"V Fran\u00e7ois-Lavet","year":"2018","unstructured":"Fran\u00e7ois-Lavet, V., Henderson, P., Islam, R., Bellemare, M.G., Pineau, J.: An introduction to deep reinforcement learning. Found. Trends Mach. Learn. 11(3\u20134), 219\u2013354 (2018)","journal-title":"Found. Trends Mach. Learn."},{"key":"25_CR11","unstructured":"Goodfellow, I.J., Mirza, M., Da, X., Courville, A.C., Bengio, Y.: An empirical investigation of catastrophic forgetting in gradient-based neural networks. CoRR abs\/1312.6211 (2013). http:\/\/arxiv.org\/abs\/1312.6211"},{"key":"25_CR12","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: International Conference on Learning Representations (ICLR) (2016)"},{"issue":"3\u20134","key":"25_CR13","first-page":"293","volume":"8","author":"LJ Lin","year":"1992","unstructured":"Lin, L.J.: Self-improving reactive agents based on reinforcement learning, planning and teaching. Mach. Learn. 8(3\u20134), 293\u2013321 (1992)","journal-title":"Mach. Learn."},{"issue":"7540","key":"25_CR14","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)","journal-title":"Nature"},{"issue":"1","key":"25_CR15","first-page":"1","volume":"41","author":"Q Liu","year":"2018","unstructured":"Liu, Q., et al.: A survey on deep reinforcement learning. Chin. J. Comput. 41(1), 1\u201327 (2018)","journal-title":"Chin. J. Comput."},{"key":"25_CR16","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. In: International Conference on Learning Representations (ICLR) (2016)"},{"key":"25_CR17","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M.I., Moritz, P.: Trust region policy optimization. In: Proceedings of the 32nd International Conference on Machine Learning (ICML) (2015)"},{"key":"25_CR18","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR abs\/1707.06347 (2017). http:\/\/arxiv.org\/abs\/1707.06347"},{"issue":"7587","key":"25_CR19","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"issue":"7676","key":"25_CR20","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of Go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"key":"25_CR21","volume-title":"Reinforcement Learning - An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning - An Introduction, 2nd edn. MIT Press, Cambridge (2018)","edition":"2"},{"issue":"1","key":"25_CR22","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1145\/3147.3165","volume":"11","author":"JS Vitter","year":"1985","unstructured":"Vitter, J.S.: Random sampling with a reservoir. ACM Trans. Math. Softw. (TOMS) 11(1), 37\u201357 (1985)","journal-title":"ACM Trans. Math. Softw. (TOMS)"},{"key":"25_CR23","unstructured":"Zhang, L., et al.: A framework of dual replay buffer: balancing forgetting and generalization in reinforcement learning. In: Workshop on Scaling Up Reinforcement Learning (SURL), International Joint Conference on Artificial Intelligence (IJCAI) (2019)"},{"issue":"1","key":"25_CR24","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/s11704-017-6222-6","volume":"13","author":"S Zhong","year":"2019","unstructured":"Zhong, S., Liu, Q., Zhang, Z., Fu, Q.: Efficient reinforcement learning in continuous state and action spaces with Dyna and policy approximation. Front. Comput. Sci. 13(1), 106\u2013126 (2019)","journal-title":"Front. Comput. Sci."}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63833-7_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T11:00:05Z","timestamp":1710327605000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-63833-7_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030638320","9783030638337"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63833-7_25","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":"20 November 2020","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":"Bangkok","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","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":"18 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apnns.org\/ICONIP2020","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"618","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":"187","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":"189","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":"30% - 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":"3.18","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":"3.68","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to COVID-19 pandemic the conference was held virtually.","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)"}}]}}