{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T13:47:11Z","timestamp":1726062431021},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030374938"},{"type":"electronic","value":"9783030374945"}],"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\/978-3-030-37494-5_12","type":"book-chapter","created":{"date-parts":[[2019,12,14]],"date-time":"2019-12-14T15:02:38Z","timestamp":1576335758000},"page":"224-245","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Wide and Deep Reinforcement Learning Extended for Grid-Based Action Games"],"prefix":"10.1007","author":[{"given":"Juan M.","family":"Montoya","sequence":"first","affiliation":[]},{"given":"Christoph","family":"Doell","sequence":"additional","affiliation":[]},{"given":"Christian","family":"Borgelt","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,15]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Bohez, S., Verbelen, T., De Coninck, E., Vankeirsbilck, B., Simoens, P., Dhoedt, B.: Sensor fusion for robot control through deep reinforcement learning. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2365\u20132370. IEEE, September 2017","DOI":"10.1109\/IROS.2017.8206048"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, H.T., et al.: Wide & deep learning for recommender systems. In: Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, DLRS 2016, pp. 7\u201310. ACM, New York (2016)","DOI":"10.1145\/2988450.2988454"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"DeNero, J., Klein, D.: Teaching introductory artificial intelligence with pac-man. In: Proceedings of the Symposium on Educational Advances in Artificial Intelligence, pp. 1885\u20131889 (2010)","DOI":"10.1155\/2010\/629869"},{"key":"12_CR4","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)"},{"key":"12_CR5","unstructured":"van Hasselt, H.P., Guez, A., Hessel, M., Mnih, V., Silver, D.: Learning values across many orders of magnitude. In: Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, Barcelona, Spain, 5\u201310 December 2016, pp. 4287\u20134295 (2016)"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., Meger, D.: Deep reinforcement learning that matters. In: Proceedings of the Thirtieth-Second AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI Press (2018)","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"12_CR7","unstructured":"Kalashnikov, D., et al.: QT-Opt: scalable deep reinforcement learning for vision-based robotic. CoRR abs\/1806.10293 (2018)"},{"key":"12_CR8","unstructured":"Kim, H.J., Jordan, M.I., Sastry, S., Ng, A.Y.: Autonomous helicopter flight via reinforcement learning. In: Thrun, S., Saul, L.K., Sch\u00f6lkopf, B. (eds.) Advances in Neural Information Processing Systems 16, pp. 799\u2013806. MIT Press (2004)"},{"key":"12_CR9","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"3-4","key":"12_CR10","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/BF00992699","volume":"8","author":"Long-Ji Lin","year":"1992","unstructured":"Lin, L.J.: Self-improving reactive agents based on reinforcement learning, Plann. Teach. Machine Learning 8(3), 293\u2013321 (1992). https:\/\/doi.org\/10.1007\/BF00992699","journal-title":"Machine Learning"},{"issue":"7540","key":"12_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)","journal-title":"Nature"},{"key":"12_CR12","doi-asserted-by":"publisher","unstructured":"Montoya., J.M., Borgelt., C.: Wide and deep reinforcement learning for grid-based action games. In: Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, pp. 50\u201359. INSTICC, SciTePress (2019). https:\/\/doi.org\/10.5220\/0007313200500059","DOI":"10.5220\/0007313200500059"},{"key":"12_CR13","unstructured":"van der Ouderaa, T.: Deep Reinforcement Learning in Pac-Man (2016). Bachelor thesis, University of Amsterdam"},{"key":"12_CR14","unstructured":"Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach. Pearson Education, 3 edn. (2003)"},{"key":"12_CR15","unstructured":"Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning (71 2018), working Second Edition"},{"key":"12_CR16","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards. Ph.D. thesis, King\u2019s College, Cambridge, UK (1989). http:\/\/www.cs.rhul.ac.uk\/~chrisw\/new_thesis.pdf"}],"container-title":["Lecture Notes in Computer Science","Agents and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-37494-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T13:17:49Z","timestamp":1665235069000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-37494-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030374938","9783030374945"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-37494-5_12","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":"15 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICAART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Agents and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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":"19 February 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 February 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icaart2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icaart.org\/","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":"PRIMORIS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"202","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":"46","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":"66","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":"23% - 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":"4","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":"36 poster papers were also accepted. 17 of the 46 accepted full papers are included in LNAI 11978.","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)"}}]}}