{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T01:20:00Z","timestamp":1742952000843,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030137083"},{"type":"electronic","value":"9783030137090"}],"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\/978-3-030-13709-0_22","type":"book-chapter","created":{"date-parts":[[2019,2,13]],"date-time":"2019-02-13T18:09:04Z","timestamp":1550081344000},"page":"264-275","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Crawling in Rogue\u2019s Dungeons with (Partitioned) A3C"],"prefix":"10.1007","author":[{"given":"Andrea","family":"Asperti","sequence":"first","affiliation":[]},{"given":"Daniele","family":"Cortesi","sequence":"additional","affiliation":[]},{"given":"Francesco","family":"Sovrano","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,2,14]]},"reference":[{"unstructured":"RMSPropOptimizer. https:\/\/www.tensorflow.org\/api_docs\/python\/tf\/train\/RMSPropOptimizer","key":"22_CR1"},{"unstructured":"Asperti, A., Cortesi, D., Sovrano, F.: Partitioned A3C for rogueinabox. https:\/\/github.com\/Francesco-Sovrano\/Partitioned-A3C-for-RogueInABox","key":"22_CR2"},{"key":"22_CR3","first-page":"362","volume":"12","author":"A Asperti","year":"2017","unstructured":"Asperti, A., Pieri, C.D., Maldini, M., Pedrini, G., Sovrano, F.: A modular deep-learning environment for rogue. WSEAS Trans. Syst. Control 12, 362\u2013373 (2017). http:\/\/www.wseas.org\/multimedia\/journals\/control\/2017\/a785903-070.php","journal-title":"WSEAS Trans. Syst. Control"},{"key":"22_CR4","first-page":"146","volume":"2","author":"A Asperti","year":"2017","unstructured":"Asperti, A., Pieri, C.D., Pedrini, G.: Rogueinabox: an environment for rogue like learning. Int. J. Comput. 2, 146\u2013154 (2017). http:\/\/www.iaras.org\/iaras\/filedownloads\/ijc\/2017\/006-0022(2017).pdf","journal-title":"Int. J. Comput."},{"key":"22_CR5","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. (JAIR) 47, 253\u2013279 (2013). https:\/\/doi.org\/10.1613\/jair.3912","journal-title":"J. Artif. Intell. Res. (JAIR)"},{"key":"22_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/978-3-319-24589-8_20","volume-title":"Entertainment Computing - ICEC 2015","author":"V Cerny","year":"2015","unstructured":"Cerny, V., Dechterenko, F.: Rogue-like games as a playground for artificial intelligence \u2013 evolutionary approach. In: Chorianopoulos, K., Divitini, M., Hauge, J.B., Jaccheri, L., Malaka, R. (eds.) ICEC 2015. LNCS, vol. 9353, pp. 261\u2013271. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24589-8_20"},{"unstructured":"Dilokthanakul, N., Kaplanis, C., Pawlowski, N., Shanahan, M.: Feature control as intrinsic motivation for hierarchical reinforcement learning. CoRR abs\/1705.06769 (2017). http:\/\/arxiv.org\/abs\/1705.06769","key":"22_CR7"},{"unstructured":"van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. CoRR abs\/1509.06461 (2015). http:\/\/arxiv.org\/abs\/1509.06461","key":"22_CR8"},{"unstructured":"Jaderberg, M., et al.: Reinforcement learning with unsupervised auxiliary tasks. CoRR abs\/1611.05397 (2016). http:\/\/arxiv.org\/abs\/1611.05397","key":"22_CR9"},{"unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems: Annual Conference on Neural Information Processing Systems 2015, Montreal, Quebec, Canada, 7\u201312 December 2015, vol. 28, pp. 2017\u20132025 (2015). http:\/\/papers.nips.cc\/paper\/5854-spatial-transformer-networks","key":"22_CR10"},{"doi-asserted-by":"crossref","unstructured":"Kempka, M., Wydmuch, M., Runc, G., Toczek, J., Jaskowski, W.: ViZDoom: a doom-based AI research platform for visual reinforcement learning. CoRR abs\/1605.02097 (2016). http:\/\/arxiv.org\/abs\/1605.02097","key":"22_CR11","DOI":"10.1109\/CIG.2016.7860433"},{"doi-asserted-by":"publisher","unstructured":"Klyubin, A.S., Polani, D., Nehaniv, C.L.: Empowerment: a universal agent-centric measure of control. In: Proceedings of the IEEE Congress on Evolutionary Computation, CEC 2005, Edinburgh, UK, 2\u20134 September 2005, pp. 128\u2013135 (2005). https:\/\/doi.org\/10.1109\/CEC.2005.1554676","key":"22_CR12","DOI":"10.1109\/CEC.2005.1554676"},{"unstructured":"Kulkarni, T.D., Narasimhan, K., Saeedi, A., Tenenbaum, J.B.: Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. CoRR abs\/1604.06057 (2016). http:\/\/arxiv.org\/abs\/1604.06057","key":"22_CR13"},{"unstructured":"Miyoshi, K.: Unreal implementation. https:\/\/github.com\/miyosuda\/unreal","key":"22_CR14"},{"unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. CoRR abs\/1602.01783 (2016). http:\/\/arxiv.org\/abs\/1602.01783","key":"22_CR15"},{"issue":"7540","key":"22_CR16","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). https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"unstructured":"Singh, S.P., Barto, A.G., Chentanez, N.: Intrinsically motivated reinforcement learning. In: Advances in Neural Information Processing Systems: Neural Information Processing Systems, NIPS 2004, Vancouver, British Columbia, Canada, 13\u201318 December 2004, vol. 17, pp. 1281\u20131288 (2004). http:\/\/papers.nips.cc\/paper\/2552-intrinsically-motivated-reinforcement-learning","key":"22_CR17"},{"unstructured":"Song, Y., Xu, M., Zhang, S., Huo, L.: Generalization tower network: a novel deep neural network architecture for multi-task learning. CoRR abs\/1710.10036 (2017). http:\/\/arxiv.org\/abs\/1710.10036","key":"22_CR18"},{"issue":"4\u20135","key":"22_CR19","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1016\/S0893-6080(99)00024-6","volume":"12","author":"R Sun","year":"1999","unstructured":"Sun, R., Peterson, T.: Multi-agent reinforcement learning: weighting and partitioning. Neural Netw. 12(4\u20135), 727\u2013753 (1999). https:\/\/doi.org\/10.1016\/S0893-6080(99)00024-6","journal-title":"Neural Netw."},{"key":"22_CR20","volume-title":"Introduction to Reinforcement Learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning, 1st edn. MIT Press, Cambridge (1998)","edition":"1"},{"unstructured":"Vezhnevets, A.S., et al.: Feudal networks for hierarchical reinforcement learning. CoRR abs\/1703.01161 (2017). http:\/\/arxiv.org\/abs\/1703.01161","key":"22_CR21"},{"unstructured":"Wang, Z.: Sample efficient actor-critic with experience replay (2016)","key":"22_CR22"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-13709-0_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T14:58:17Z","timestamp":1709823497000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-13709-0_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030137083","9783030137090"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-13709-0_22","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":"14 February 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning, Optimization, and Data Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Volterra","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2018.icas.xyz\/","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, in-house system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"126","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":"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":"37% - 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":"5","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":"1.5","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)"}}]}}