{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T19:11:12Z","timestamp":1726081872318},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030461324"},{"type":"electronic","value":"9783030461331"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-46133-1_4","type":"book-chapter","created":{"date-parts":[[2020,4,30]],"date-time":"2020-04-30T07:08:58Z","timestamp":1588230538000},"page":"53-68","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Safe Policy Improvement with Soft Baseline Bootstrapping"],"prefix":"10.1007","author":[{"given":"Kimia","family":"Nadjahi","sequence":"first","affiliation":[]},{"given":"Romain","family":"Laroche","sequence":"additional","affiliation":[]},{"given":"R\u00e9mi","family":"Tachet des Combes","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,4,30]]},"reference":[{"key":"4_CR1","unstructured":"Bellemare, M., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying count-based exploration and intrinsic motivation. In: Proceedings of the 29th Advances in Neural Information Processing Systems (NIPS) (2016)"},{"key":"4_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-61578-8","volume-title":"The Simplex Method: A Probabilistic Analysis","author":"KH Borgwardt","year":"1987","unstructured":"Borgwardt, K.H.: The Simplex Method: A Probabilistic Analysis. Springer, Heidelberg (1987). https:\/\/doi.org\/10.1007\/978-3-642-61578-8"},{"key":"4_CR3","unstructured":"Burda, Y., Edwards, H., Storkey, A., Klimov, O.: Exploration by random network distillation. In: Proceedings of the 7th International Conference on Learning Representations (ICLR) (2019)"},{"key":"4_CR4","series-title":"Rand Corporation Research Study","doi-asserted-by":"publisher","DOI":"10.7249\/R366","volume-title":"Linear Programming and Extensions","author":"G Dantzig","year":"1963","unstructured":"Dantzig, G.: Linear Programming and Extensions. Rand Corporation Research Study. Princeton Univ. Press, Princeton (1963)"},{"key":"4_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/b97283","volume-title":"Linear Programming 2: Theory and Extensions","author":"GB Dantzig","year":"2003","unstructured":"Dantzig, G.B., Thapa, M.N.: Linear Programming 2: Theory and Extensions. Springer, New York (2003). https:\/\/doi.org\/10.1007\/b97283"},{"key":"4_CR6","first-page":"503","volume":"6","author":"D Ernst","year":"2005","unstructured":"Ernst, D., Geurts, P., Wehenkel, L.: Tree-based batch mode reinforcement learning. J. Mach. Learn. Res. 6, 503\u2013556 (2005)","journal-title":"J. Mach. Learn. Res."},{"key":"4_CR7","unstructured":"Fox, L., Choshen, L., Loewenstein, Y.: Dora the explorer: directed outreaching reinforcement action-selection. In: Proceedings of the 6th International Conference on Learning Representations (ICLR) (2018)"},{"key":"4_CR8","unstructured":"Geist, M., Scherrer, B., Pietquin, O.: A theory of regularized Markov decision processes. In: Proceedings of the 36th International Conference on Machine Learning (ICML) (2019)"},{"issue":"3","key":"4_CR9","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1016\/j.ejor.2011.09.017","volume":"218","author":"J Gondzio","year":"2012","unstructured":"Gondzio, J.: Interior point methods 25 years later. Eur. J. Oper. Res. 218(3), 587\u2013601 (2012)","journal-title":"Eur. J. Oper. Res."},{"key":"4_CR10","unstructured":"Guez, A., Vincent, R.D., Avoli, M., Pineau, J.: Adaptive treatment of epilepsy via batch-mode reinforcement learning. In: Proceedings of the 23rd AAAI Conference on Artificial Intelligence, pp. 1671\u20131678 (2008)"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. arXiv preprint arXiv:1502.01852 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"issue":"2","key":"4_CR12","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1287\/moor.1040.0129","volume":"30","author":"GN Iyengar","year":"2005","unstructured":"Iyengar, G.N.: Robust dynamic programming. Math. Oper. Res. 30(2), 257\u2013280 (2005)","journal-title":"Math. Oper. Res."},{"key":"4_CR13","unstructured":"Kakade, S., Langford, J.: Approximately optimal approximate reinforcement learning. In: Proceedings of the 19th International Conference on Machine Learning (ICML), vol. 2, pp. 267\u2013274 (2002)"},{"key":"4_CR14","first-page":"159","volume-title":"Inequalities","author":"V Klee","year":"1972","unstructured":"Klee, V., Minty, G.J.: How good is the simplex algorithm? In: Shisha, O. (ed.) Inequalities, vol. III, pp. 159\u2013175. Academic Press, New York (1972)"},{"key":"4_CR15","series-title":"Adaptation, Learning, and Optimization","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/978-3-642-27645-3_2","volume-title":"Reinforcement Learning","author":"S Lange","year":"2012","unstructured":"Lange, S., Gabel, T., Riedmiller, M.: Batch reinforcement learning. In: Wiering, M., van Otterlo, M. (eds.) Reinforcement Learning. Adaptation, Learning, and Optimization, vol. 12, pp. 45\u201373. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3_2"},{"key":"4_CR16","unstructured":"Laroche, R., Trichelair, P., Tachet des Combes, R.: Safe policy improvement with baseline bootstrapping. In: Proceedings of the 36th International Conference on Machine Learning (ICML) (2019)"},{"issue":"7540","key":"4_CR17","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 (2015)","journal-title":"Nature"},{"issue":"5","key":"4_CR18","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1287\/opre.1050.0216","volume":"53","author":"A Nilim","year":"2005","unstructured":"Nilim, A., El Ghaoui, L.: Robust control of Markov decision processes with uncertain transition matrices. Oper. Res. 53(5), 780\u2013798 (2005)","journal-title":"Oper. Res."},{"key":"4_CR19","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS-W (2017)"},{"key":"4_CR20","unstructured":"Petrik, M., Ghavamzadeh, M., Chow, Y.: Safe policy improvement by minimizing robust baseline regret. In: Proceedings of the 29th Advances in Neural Information Processing Systems (NIPS) (2016)"},{"key":"4_CR21","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/11564096_32","volume-title":"Machine Learning: ECML 2005","author":"M Riedmiller","year":"2005","unstructured":"Riedmiller, M.: Neural fitted Q iteration \u2013 first experiences with a data efficient neural reinforcement learning method. In: Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., Torgo, L. (eds.) ECML 2005. LNCS (LNAI), vol. 3720, pp. 317\u2013328. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11564096_32"},{"key":"4_CR22","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: Proceedings of the 32nd International Conference on Machine Learning (ICML) (2015)"},{"key":"4_CR23","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Sim\u00e3o, T.D., Spaan, M.T.J.: Safe policy improvement with baseline bootstrapping in factored environments. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v33i01.33014967"},{"key":"4_CR25","unstructured":"Singh, S.P., Kearns, M.J., Litman, D.J., Walker, M.A.: Reinforcement learning for spoken dialogue systems. In: Proceedings of the 13th Advances in Neural Information Processing Systems (NIPS), pp. 956\u2013962 (1999)"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"4_CR27","unstructured":"Thomas, P.S.: Safe reinforcement learning. Ph.D. thesis, Stanford university (2015)"},{"key":"4_CR28","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw. Mach. Learn. 4(2), 26\u201331 (2012)"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. CoRR, abs\/1509.06461 (2015)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"4_CR30","unstructured":"Weissman, T., Ordentlich, E., Seroussi, G., Verdu, S., Weinberger, M.J.: Inequalities for the L1 deviation of the empirical distribution. Hewlett-Packard Labs, Technical report (2003)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-46133-1_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T16:51:46Z","timestamp":1666457506000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-46133-1_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030461324","9783030461331"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-46133-1_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"30 April 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"W\u00fcrzburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"16 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ecmlpkdd2019.org\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"733","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":"130","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":"18% - 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":"3.04","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":"5.3","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)"}},{"value":"ECML PKDD Workshops Information: single-blind review, submissions: 200, full papers accepted: 70, short papers accepted: 46","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)"}}]}}