{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:58:52Z","timestamp":1743087532870,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030348847"},{"type":"electronic","value":"9783030348854"}],"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\/978-3-030-34885-4_6","type":"book-chapter","created":{"date-parts":[[2019,12,9]],"date-time":"2019-12-09T00:02:46Z","timestamp":1575849766000},"page":"78-90","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Understanding Structure of Concurrent Actions"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6227-9578","authenticated-orcid":false,"given":"Perusha","family":"Moodley","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0284-4114","authenticated-orcid":false,"given":"Benjamin","family":"Rosman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6832-2298","authenticated-orcid":false,"given":"Xia","family":"Hong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,11,19]]},"reference":[{"key":"6_CR1","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. In: Proceedings of the 24th International Conference on Artificial Intelligence, pp. 4148\u20134152. IJCAI 2015, AAAI Press (2015). \nhttp:\/\/dl.acm.org\/citation.cfm?id=2832747.2832830"},{"key":"6_CR2","unstructured":"Chandak, Y., Theocharous, G., Kostas, J., Jordan, S., Thomas, P.: Learning action representations for reinforcement learning. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 97, pp. 941\u2013950. PMLR, Long Beach, California, USA (09\u201315 June 2019). \nhttp:\/\/proceedings.mlr.press\/v97\/chandak19a.html"},{"key":"6_CR3","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. AAAI\/IAAI (1998)"},{"key":"6_CR4","unstructured":"Dimakopoulou, M., Van Roy, B.: Coordinated exploration in concurrent reinforcement learning. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 1271\u20131279. PMLR, Stockholmsm\u00e4ssan, Stockholm Sweden (2018)"},{"key":"6_CR5","doi-asserted-by":"publisher","unstructured":"Harmer, J., et al.: Imitation learning with concurrent actions in 3D games. In: 2018 IEEE Conference on Computational Intelligence and Games, CIG 2018, Maastricht, The Netherlands, August 14\u201317, 2018, pp. 1\u20138 (2018). \nhttps:\/\/doi.org\/10.1109\/CIG.2018.8490398","DOI":"10.1109\/CIG.2018.8490398"},{"issue":"4","key":"6_CR6","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/s11222-007-9033-z","volume":"17","author":"U Luxburg","year":"2007","unstructured":"Luxburg, U.: A tutorial on spectral clustering. Stat. Comput. 17(4), 395\u2013416 (2007). \nhttps:\/\/doi.org\/10.1007\/s11222-007-9033-z","journal-title":"Stat. Comput."},{"key":"6_CR7","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. CoRR abs\/1301.3781 (2013). \nhttp:\/\/dblp.uni-trier.de\/db\/journals\/corr\/corr1301.html\/abs-1301-3781"},{"key":"6_CR8","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning, vol. 48, pp. 1928\u20131937. ICML 2016, JMLR.org (2016). \nhttp:\/\/dl.acm.org\/citation.cfm?id=3045390.3045594"},{"key":"6_CR9","unstructured":"Ng, A.Y., Jordan, M.I., Weiss, Y.: On spectral clustering: analysis and an algorithm. In: Dietterich, T.G., Becker, S., Ghahramani, Z. (eds.) Advances in Neural Information Processing Systems, vol. 14, pp. 849\u2013856. MIT Press, Cambridge (2002). \nhttp:\/\/papers.nips.cc\/paper\/2092-on-spectral-clustering-analysis-and-an-algorithm.pdf"},{"key":"6_CR10","unstructured":"Rohanimanesh, K.: Concurrent decision making in Markov decision processes. Citeseer (2006)"},{"issue":"2","key":"6_CR11","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1109\/TAMD.2015.2419715","volume":"7","author":"B Rosman","year":"2015","unstructured":"Rosman, B., Ramamoorthy, S.: Action priors for learning domain invariances. IEEE Trans. Auton. Ment. Dev. 7(2), 107\u2013118 (2015)","journal-title":"IEEE Trans. Auton. Ment. Dev."},{"key":"6_CR12","unstructured":"Sharma, S., Suresh, A., Ramesh, R., Ravindran, B.: Learning to factor policies and action-value functions: factored action space representations for deep reinforcement learning. CoRR abs\/1705.07269 (2017). \nhttp:\/\/arxiv.org\/abs\/1705.07269"},{"key":"6_CR13","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, 354 (2017). \nhttps:\/\/doi.org\/10.1038\/nature24270","journal-title":"Nature"},{"key":"6_CR14","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998). \nhttp:\/\/www.cs.ualberta.ca\/~sutton\/book\/the-book.html"},{"key":"6_CR15","unstructured":"Tennenholtz, G., Mannor, S.: The natural language of actions. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 97, pp. 6196\u20136205. PMLR, Long Beach, California, USA (09\u201315 Jun 2019). \nhttp:\/\/proceedings.mlr.press\/v97\/tennenholtz19a.html"},{"key":"6_CR16","unstructured":"Vinyals, O., et al.: Starcraft II: a new challenge for reinforcement learning. CoRR abs\/1708.04782 (2017). \nhttp:\/\/arxiv.org\/abs\/1708.04782"},{"key":"6_CR17","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1007\/978-3-319-42911-3_48","volume-title":"PRICAI 2016: Trends in Artificial Intelligence","author":"H Wang","year":"2016","unstructured":"Wang, H., Yu, Y.: Exploring multi-action relationship in reinforcement learning. In: Booth, R., Zhang, M.-L. (eds.) PRICAI 2016. LNCS (LNAI), vol. 9810, pp. 574\u2013587. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-42911-3_48"},{"key":"6_CR18","unstructured":"Zahavy, T., Haroush, M., Merlis, N., Mankowitz, D.J., Mannor, S.: Learn what not to learn: action elimination with deep reinforcement learning. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 31, pp. 3562\u20133573. Curran Associates, Inc. (2018). \nhttp:\/\/papers.nips.cc\/paper\/7615-learn-what-not-to-learn-action-elimination-with-deep-reinforcement-learning.pdf"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence XXXVI"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-34885-4_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,22]],"date-time":"2020-04-22T10:05:50Z","timestamp":1587549950000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-34885-4_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030348847","9783030348854"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-34885-4_6","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":"19 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SGAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Innovative Techniques and Applications of Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambridge","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"17 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"39","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sgai2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/bcs-sgai.org\/ai2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}