{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T13:06:07Z","timestamp":1726059967977},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030352875"},{"type":"electronic","value":"9783030352882"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-35288-2_2","type":"book-chapter","created":{"date-parts":[[2019,11,25]],"date-time":"2019-11-25T00:02:57Z","timestamp":1574640177000},"page":"15-27","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Helping an Agent Reach a Different Goal by Action Transfer in Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Yuchen","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fenghui","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minjie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,11,25]]},"reference":[{"key":"2_CR1","unstructured":"Amir, O., Kamar, E., Kolobov, A., Grosz, B.J.: Interactive teaching strategies for agent training. In: Proceedings of the 25th International Joint Conferences on Artificial Intelligence. pp. 804\u2013811 (2016)"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Chernova, S., Veloso, M.: Confidence-based policy learning from demonstration using gaussian mixture models. In: Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems. pp. 1315\u20131322 (2007)","DOI":"10.1145\/1329125.1329407"},{"key":"2_CR3","unstructured":"Da Silva, F.L., Glatt, R., Costa, A.H.R.: Simultaneously learning and advising in multiagent reinforcement learning. In: Proceedings of the 16th Conference on Autonomous Agents and Multiagent Systems. pp. 1100\u20131108 (2017)"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez, F., Veloso, M.: Probabilistic policy reuse in a reinforcement learning agent. In: Proceedings of the fifth International Ioint Conference on Autonomous Agents and Multiagent Systems. pp. 720\u2013727. ACM (2006)","DOI":"10.1145\/1160633.1160762"},{"key":"2_CR5","unstructured":"Puterman, M.L.: Markov decision processes: discrete stochastic dynamic programming. John Wiley & Sons (2014)"},{"key":"2_CR6","unstructured":"Sherstov, A.A., Stone, P.: Improving action selection in mdp\u2019s via knowledge transfer. In: Proceedings of the 20th National Conference on Artificial Intelligence. vol. 5, pp. 1024\u20131029 (2005)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"issue":"1","key":"2_CR8","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., Torrey, L.: Reinforcement learning agents providing advice in complex video games. Connection Science 26(1), 45\u201363 (2014)","journal-title":"Connection Science"},{"key":"2_CR9","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: A survey. Journal of Machine Learning Research 10, 1633\u20131685 (2009)","journal-title":"Journal of Machine Learning Research"},{"key":"2_CR10","unstructured":"Torrey, L., Taylor, M.: Teaching on a budget: Agents advising agents in reinforcement learning. In: Proceedings of the 12th International Conference on Autonomous Agents and Multiagent Systems. pp. 1053\u20131060 (2013)"},{"issue":"3\u20134","key":"2_CR11","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Machine Learning 8(3\u20134), 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Wilson, A., Fern, A., Ray, S., Tadepalli, P.: Multi-task reinforcement learning: a hierarchical bayesian approach. In: Proceedings of the 24th International Conference on Machine Learning. pp. 1015\u20131022. ACM (2007)","DOI":"10.1145\/1273496.1273624"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Ye, D., Zhu, T., Zhou, W., Philip, S.Y.: Differentially private malicious agent avoidance in multiagent advising learning. IEEE Transactions on Cybernetics (2019)","DOI":"10.1109\/TCYB.2019.2906574"},{"issue":"12","key":"2_CR14","doi-asserted-by":"publisher","first-page":"2853","DOI":"10.1109\/TCYB.2014.2387277","volume":"45","author":"C Yu","year":"2015","unstructured":"Yu, C., Zhang, M., Ren, F., Tan, G.: Multiagent learning of coordination in loosely coupled multiagent systems. IEEE Transactions on Cybernetics 45(12), 2853\u20132867 (2015)","journal-title":"IEEE Transactions on Cybernetics"},{"key":"2_CR15","unstructured":"Zhan, Y., Ammar, H.B., Taylor, M.E.: Theoretically-grounded policy advice from multiple teachers in reinforcement learning settings with applications to negative transfer. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence. pp. 2315\u20132321 (2016)"}],"container-title":["Lecture Notes in Computer Science","AI 2019: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-35288-2_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,25]],"date-time":"2019-11-25T00:28:15Z","timestamp":1574641695000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-35288-2_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030352875","9783030352882"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-35288-2_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"25 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Adelaide, SA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/nugget.unisa.edu.au\/AI2019\/index.php","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":"115","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":"48","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":"42% - 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":"3.4","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":"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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}