{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:28:51Z","timestamp":1742988531015,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030893699"},{"type":"electronic","value":"9783030893705"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-89370-5_4","type":"book-chapter","created":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T01:02:59Z","timestamp":1635728579000},"page":"46-59","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Off-Policy Training for Truncated TD($$\\lambda $$) Boosted Soft Actor-Critic"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0500-0141","authenticated-orcid":false,"given":"Shiyu","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8294-6315","authenticated-orcid":false,"given":"Hang","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3228-9166","authenticated-orcid":false,"given":"Ting","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,11,1]]},"reference":[{"key":"4_CR1","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"4_CR2","unstructured":"Chen, G., Li, D., Xu, R.: Context-aware active multi-step reinforcement learning. arXiv preprint arXiv:1911.04107 (2019)"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"De Asis, K., Hernandez-Garcia, J.F., Holland, G.Z., Sutton, R.S.: Multi-step reinforcement learning: a unifying algorithm (2017)","DOI":"10.1609\/aaai.v32i1.11631"},{"key":"4_CR4","unstructured":"Espeholt, L., et al.: IMPALA: scalable distributed deep-RL with importance weighted actor-learner architectures. arXiv: Learning (2018)"},{"key":"4_CR5","unstructured":"Fujimoto, S., Van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods (2018)"},{"key":"4_CR6","unstructured":"Gruslys, A., Dabney, W., Azar, M.G., Piot, B., Bellemare, M.G., Munos, R.: The reactor: a fast and sample-efficient actor-critic agent for reinforcement learning. arXiv:ArtificialIntelligence (2017)"},{"key":"4_CR7","unstructured":"Haarnoja, T., Tang, H., Abbeel, P., Levine, S.: Reinforcement learning with deep energy-based policies. arXiv preprint arXiv:1702.08165 (2017)"},{"key":"4_CR8","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv preprint arXiv:1801.01290 (2018)"},{"key":"4_CR9","unstructured":"Haarnoja, T., et al.: Soft actor-critic algorithms and applications (2018)"},{"key":"4_CR10","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/978-3-319-46379-7_21","volume-title":"Algorithmic Learning Theory","author":"A Harutyunyan","year":"2016","unstructured":"Harutyunyan, A., Bellemare, M.G., Stepleton, T., Munos, R.: Q($$\\lambda $$) with off-policy corrections. In: Ortner, R., Simon, H.U., Zilles, S. (eds.) ALT 2016. LNCS (LNAI), vol. 9925, pp. 305\u2013320. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46379-7_21"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Hessel, M., et al.: Rainbow: combining improvements in deep reinforcement learning, pp. 3215\u20133222 (2018)","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"4_CR12","unstructured":"Horgan, D., et al.: Distributed prioritized experience replay. arXiv:Learning (2018)"},{"key":"4_CR13","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"issue":"7540","key":"4_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 (2015)","journal-title":"Nature"},{"key":"4_CR15","unstructured":"Munos, R., Stepleton, T., Harutyunyan, A., Bellemare, M.G.: Safe and efficient off-policy reinforcement learning, pp. 1054\u20131062 (2016)"},{"key":"4_CR16","unstructured":"Precup, D., Sutton, R.S., Singh, S.P.: Eligibility traces for off-policy policy evaluation. In: Proceedings of the Seventeenth International Conference on Machine Learning. ICML 2000, pp. 759\u2013766. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (2000)"},{"key":"4_CR17","unstructured":"Rummery, G.A., Niranjan, M.: On-line Q-learning Using Connectionist Systems, vol. 37. University of Cambridge, Department of Engineering Cambridge, UK (1994)"},{"key":"4_CR18","unstructured":"Seijen, H., Sutton, R.: True online td (lambda). In: International Conference on Machine Learning, PMLR, vol. 32, pp. 692\u2013700 (2014)"},{"issue":"1","key":"4_CR19","first-page":"9","volume":"3","author":"RS Sutton","year":"1988","unstructured":"Sutton, R.S.: Learning to predict by the method of temporal differences. Mach. Learn. 3(1), 9\u201344 (1988)","journal-title":"Mach. Learn."},{"key":"4_CR20","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":"4_CR21","unstructured":"Van Hasselt, H., Doron, Y., Strub, F., Hessel, M., Sonnerat, N., Modayil, J.: Deep reinforcement learning and the deadly triad (2018)"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. Computer Ence (2015)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Van Seijen, H., Van Hasselt, H., Whiteson, S., Wiering, M.: A theoretical and empirical analysis of expected Sarsa. In: 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, pp. 177\u2013184 (2009)","DOI":"10.1109\/ADPRL.2009.4927542"},{"key":"4_CR24","unstructured":"Wang, Z., Schaul, T., Hessel, M., Van Hasselt, H., Lanctot, M., De Freitas, N.: Dueling network architectures for deep reinforcement learning (2015)"},{"key":"4_CR25","unstructured":"Watkins, C.J.C.H.: Learning from delayed rewards. Ph.D. thesis, Cambridge University (1989)"},{"key":"4_CR26","unstructured":"Wickham, H., Stryjewski, L.: 40 years of boxplots. American Statistician (2011)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Yang, L., Shi, M., Zheng, Q., Meng, W., Pan, G.: A unified approach for multi-step temporal-difference learning with eligibility traces in reinforcement learning (2018)","DOI":"10.24963\/ijcai.2018\/414"},{"key":"4_CR28","unstructured":"Yang, L., Zhang, Y., Zheng, Q., Li, P., Pan, G.: Gradient q$$(\\sigma , \\lambda )$$: a unified algorithm with function approximation for reinforcement learning. arXiv: Learning (2019)"},{"key":"4_CR29","unstructured":"Ziebart, B.D.: Modeling purposeful adaptive behavior with the principle of maximum causal entropy (2010)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2021: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-89370-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,14]],"date-time":"2023-01-14T06:46:58Z","timestamp":1673678818000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-89370-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030893699","9783030893705"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-89370-5_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"1 November 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2021","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"382","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":"93","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":"28","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":"24% - 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":"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)"}}]}}