{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T11:55:26Z","timestamp":1726228526456},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031408779"},{"type":"electronic","value":"9783031408786"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-40878-6_8","type":"book-chapter","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T09:03:22Z","timestamp":1693818202000},"page":"130-142","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Imperative Action Masking for\u00a0Safe Exploration in\u00a0Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Sumanta","family":"Dey","sequence":"first","affiliation":[]},{"given":"Sharat","family":"Bhat","sequence":"additional","affiliation":[]},{"given":"Pallab","family":"Dasgupta","sequence":"additional","affiliation":[]},{"given":"Soumyajit","family":"Dey","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,5]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","first-page":"1608","DOI":"10.1177\/0278364910371999","volume":"29","author":"P Abbeel","year":"2010","unstructured":"Abbeel, P., Coates, A., Ng, A.: Autonomous helicopter aerobatics through apprenticeship learning. Int. J. Robot. Res. 29, 1608\u20131639 (2010)","journal-title":"Int. J. Robot. Res."},{"key":"8_CR2","unstructured":"Achiam, J., Held, D., Tamar, A., Abbeel, P.: Constrained policy optimization. In: International Conference on Machine Learning (2017)"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., Topcu, U.: Safe reinforcement learning via shielding. In: AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"8_CR4","unstructured":"Amodei, D., Olah, C., Steinhardt, J., Christiano, P.F., Schulman, J., Man\u00e9, D.: Concrete problems in AI safety. arXiv abs\/1606.06565 (2016)"},{"key":"8_CR5","unstructured":"Berkeley, U.: UC Berkeley CS188 Intro to AI reinforcement learning. http:\/\/ai.berkeley.edu\/reinforcement.html Accessed 14 Jun 2023"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Berkenkamp, F., Moriconi, R., Schoellig, A.P., Krause, A.: Safe learning of regions of attraction for uncertain, nonlinear systems with gaussian processes. In: 2016 IEEE 55th Conference on Decision and Control (CDC), pp. 4661\u20134666 (2016)","DOI":"10.1109\/CDC.2016.7798979"},{"key":"8_CR7","unstructured":"Bharadhwaj, H., Kumar, A., Rhinehart, N., Levine, S., Shkurti, F., Garg, A.: Conservative safety critics for exploration. arXiv abs\/2010.14497 (2020)"},{"key":"8_CR8","unstructured":"Bit-Monnot, A., Leofante, F., Pulina, L., \u00c1brah\u00e1m, E., Tacchella, A.: Smartplan: a task planner for smart factories. arXiv abs\/1806.07135 (2018)"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Blum, A., Furst, M.L.: Fast planning through planning graph analysis. In: International Joint Conference on Artificial Intelligence (1995)","DOI":"10.21236\/ADA303260"},{"key":"8_CR10","unstructured":"Chow, Y., Nachum, O., Du\u00e9\u00f1ez-Guzm\u00e1n, E.A., Ghavamzadeh, M.: A lyapunov-based approach to safe reinforcement learning. In: Neural Information Processing Systems (2018)"},{"key":"8_CR11","unstructured":"Dey, S., Dasgupta, P., Dey, S.: Safe reinforcement learning through phasic safety oriented policy optimization. In: SafeAI@AAAI Conference on Artificial Intelligence (2023)"},{"key":"8_CR12","doi-asserted-by":"publisher","first-page":"5034","DOI":"10.1109\/TNSM.2022.3194566","volume":"19","author":"S Dey","year":"2022","unstructured":"Dey, S., Mujumdar, A., Dasgupta, P., Dey, S.: Adaptive safety shields for reinforcement learning-based cell shaping. IEEE Trans. Netw. Serv. Manage. 19, 5034\u20135043 (2022)","journal-title":"IEEE Trans. Netw. Serv. Manage."},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Feghhi, S., Aumayr, E., Vannella, F., Hakim, E.A., Iakovidis, G.: Safe reinforcement learning for antenna tilt optimisation using shielding and multiple baselines. arXiv abs\/2012.01296 (2020)","DOI":"10.1109\/PIMRC50174.2021.9569387"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Fulton, N., Platzer, A.: Safe reinforcement learning via formal methods: Toward safe control through proof and learning. In: AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12107"},{"key":"8_CR15","first-page":"1437","volume":"16","author":"J Garc\u00eda","year":"2015","unstructured":"Garc\u00eda, J., Fern\u00e1ndez, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16, 1437\u20131480 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"8_CR16","unstructured":"Jansen, N., K\u00f6nighofer, B., Junges, S., Serban, A.C., Bloem, R.: Safe reinforcement learning using probabilistic shields (invited paper). In: International Conference on Concurrency Theory (2020)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Nikou, A., Mujumdar, A., Orlic, M., Feljan, A.V.: Symbolic reinforcement learning for safe ran control. In: Adaptive Agents and Multi-Agent Systems (2021)","DOI":"10.1109\/ICCA54724.2022.9831850"},{"key":"8_CR18","unstructured":"Perkins, T.J., Barto, A.G.: Lyapunov design for safe reinforcement learning. J. Mach. Learn. Res. 3(null), 803\u2013832 (mar 2003)"},{"key":"8_CR19","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. MIT press (2018)"}],"container-title":["Lecture Notes in Computer Science","Explainable and Transparent AI and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-40878-6_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T09:04:22Z","timestamp":1693818262000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40878-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031408779","9783031408786"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40878-6_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EXTRAAMAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Explainable, Transparent Autonomous Agents and Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"London","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"extraamas2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/extraamas.ehealth.hevs.ch\/","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":"26","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":"15","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":"1","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":"58% - 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":"Between 3 and 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\/2","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)"}}]}}