{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T02:04:56Z","timestamp":1774577096621,"version":"3.50.1"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031164736","type":"print"},{"value":"9783031164743","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-16474-3_35","type":"book-chapter","created":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T14:16:28Z","timestamp":1662992188000},"page":"427-439","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Assessing Policy, Loss and\u00a0Planning Combinations in\u00a0Reinforcement Learning Using a\u00a0New Modular Architecture"],"prefix":"10.1007","author":[{"given":"Tiago Gaspar","family":"Oliveira","sequence":"first","affiliation":[]},{"given":"Arlindo L.","family":"Oliveira","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,13]]},"reference":[{"key":"35_CR1","unstructured":"Anthony, T., Tian, Z., Barber, D.: Thinking fast and slow with deep learning and tree search (2017)"},{"key":"35_CR2","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TSMC.1983.6313077","volume":"5","author":"AG Barto","year":"1983","unstructured":"Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans. Syst. Man Cybern. 5, 834\u2013846 (1983)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"35_CR3","unstructured":"Borges, A., Oliveira, A.: Combining off and on-policy training in model-based reinforcement learning. arXiv preprint arXiv:2102.12194 (2021)"},{"key":"35_CR4","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"35_CR5","doi-asserted-by":"publisher","unstructured":"Campbell, M., Hoane, A., hsiung Hsu, F.: Deep blue. Artif. Intell. 134(1), 57\u201383 (2002). https:\/\/doi.org\/10.1016\/S0004-3702(01)00129-1, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0004370201001291","DOI":"10.1016\/S0004-3702(01)00129-1"},{"key":"35_CR6","unstructured":"Chevalier-Boisvert, M., Willems, L., Pal, S.: Minimalistic gridworld environment for OpenAI gym (2018). https:\/\/github.com\/maximecb\/gym-minigrid"},{"key":"35_CR7","unstructured":"Cohen-Solal, Q.: Learning to play two-player perfect-information games without knowledge. arXiv preprint arXiv:2008.01188 (2020)"},{"key":"35_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/978-3-540-75538-8_7","volume-title":"Computers and Games","author":"R Coulom","year":"2007","unstructured":"Coulom, R.: Efficient selectivity and backup operators in Monte-Carlo tree search. In: van den Herik, H.J., Ciancarini, P., Donkers, H.H.L.M.J. (eds.) CG 2006. LNCS, vol. 4630, pp. 72\u201383. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-75538-8_7"},{"key":"35_CR9","unstructured":"Hamrick, J.B., et al.: Combining Q-learning and search with amortized value estimates. arXiv preprint arXiv:1912.02807 (2019)"},{"key":"35_CR10","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/11871842_29","volume-title":"Machine Learning: ECML 2006","author":"L Kocsis","year":"2006","unstructured":"Kocsis, L., Szepesv\u00e1ri, C.: Bandit based Monte-Carlo planning. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 282\u2013293. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11871842_29"},{"key":"35_CR11","unstructured":"Oh, J., Singh, S., Lee, H.: Value prediction network. arXiv preprint arXiv:1707.03497 (2017)"},{"issue":"7839","key":"35_CR12","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser, J., et al.: Mastering atari, go, chess and shogi by planning with a learned model. Nature 588(7839), 604\u2013609 (2020)","journal-title":"Nature"},{"issue":"7587","key":"35_CR13","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":"6419","key":"35_CR14","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362(6419), 1140\u20131144 (2018)","journal-title":"Science"},{"issue":"7676","key":"35_CR15","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":"35_CR16","unstructured":"de Vries, J.A., Voskuil, K.S., Moerland, T.M., Plaat, A.: Visualizing muzero models. arXiv preprint arXiv:2102.12924 (2021)"},{"key":"35_CR17","doi-asserted-by":"publisher","unstructured":"Wang, H., Emmerich, M., Preuss, M., Plaat, A.: Alternative loss functions in alphazero-like self-play. In: 2019 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 155\u2013162 (2019). https:\/\/doi.org\/10.1109\/SSCI44817.2019.9002814","DOI":"10.1109\/SSCI44817.2019.9002814"}],"container-title":["Lecture Notes in Computer Science","Progress in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16474-3_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T14:21:45Z","timestamp":1662992505000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16474-3_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031164736","9783031164743"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16474-3_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"13 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EPIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"EPIA Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"epia2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/epia2022.inesc-id.pt\/","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":"85","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":"64","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":"75% - 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":"3,7","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":"0,9","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)"}}]}}