{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T00:01:43Z","timestamp":1778716903260,"version":"3.51.4"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031171079","type":"print"},{"value":"9783031171086","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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-17108-6_12","type":"book-chapter","created":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T13:04:15Z","timestamp":1663765455000},"page":"190-206","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Training Agents to\u00a0Satisfy Timed and\u00a0Untimed Signal Temporal Logic Specifications with\u00a0Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7147-1964","authenticated-orcid":false,"given":"Nathaniel","family":"Hamilton","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4906-2179","authenticated-orcid":false,"given":"Preston K","family":"Robinette","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8021-9923","authenticated-orcid":false,"given":"Taylor T","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,1]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Aksaray, D., Jones, A., Kong, Z., Schwager, M., Belta, C.: Q-learning for robust satisfaction of signal temporal logic specifications. In: 2016 IEEE 55th Conference on Decision and Control (CDC), pp. 6565\u20136570. IEEE (2016)","DOI":"10.1109\/CDC.2016.7799279"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Balakrishnan, A., Deshmukh, J.V.: Structured reward shaping using signal temporal logic specifications. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3481\u20133486. IEEE (2019)","DOI":"10.1109\/IROS40897.2019.8968254"},{"issue":"5","key":"12_CR3","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TSMC.1983.6313077","volume":"13","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. SMC- 13(5), 834\u2013846 (1983)","journal-title":"IEEE Trans. Syst. Man Cybern. SMC-"},{"key":"12_CR4","unstructured":"Brockman, G., et al.: Openai gym (2016)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Camacho, A., Icarte, R.T., Klassen, T.Q., Valenzano, R.A., McIlraith, S.A.: LTL and beyond: formal languages for reward function specification in reinforcement learning. In: IJCAI. vol. 19, pp. 6065\u20136073 (2019)","DOI":"10.24963\/ijcai.2019\/840"},{"key":"12_CR6","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596. PMLR (2018)"},{"key":"12_CR7","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Hamilton, N., Musau, P., Lopez, D.M., Johnson, T.T.: Zero-shot policy transfer in autonomous racing: reinforcement learning vs imitation learning. In: Proceedings of the 1st IEEE International Conference on Assured Autonomy (2022)","DOI":"10.1109\/ICAA52185.2022.00011"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Hamilton, N., Schlemmer, L., Menart, C., Waddington, C., Jenkins, T., Johnson, T.T.: Sonic to knuckles: evaluations on transfer reinforcement learning. In: Unmanned Systems Technology XXII. vol. 11425, p. 114250J. International Society for Optics and Photonics (2020)","DOI":"10.1117\/12.2559546"},{"key":"12_CR10","unstructured":"Hasanbeig, M., Abate, A., Kroening, D.: Logically-constrained reinforcement learning code repository. https:\/\/github.com\/grockious\/lcrl (2020)"},{"key":"12_CR11","unstructured":"Icarte, R.T., Klassen, T., Valenzano, R., McIlraith, S.: Using reward machines for high-level task specification and decomposition in reinforcement learning. In: International Conference on Machine Learning, pp. 2107\u20132116. PMLR (2018)"},{"key":"12_CR12","unstructured":"Jothimurugan, K., Alur, R., Bastani, O.: A composable specification language for reinforcement learning tasks. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019 (2019)"},{"key":"12_CR13","unstructured":"Jothimurugan, K., Bastani, O., Alur, R.: Abstract value iteration for hierarchical reinforcement learning. In: International Conference on Artificial Intelligence and Statistics, pp. 1162\u20131170. PMLR (2021)"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Li, X., Vasile, C.I., Belta, C.: Reinforcement learning with temporal logic rewards. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3834\u20133839. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206234"},{"key":"12_CR15","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: ICLR (2016)"},{"key":"12_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1007\/978-3-540-30206-3_12","volume-title":"Formal Techniques, Modelling and Analysis of Timed and Fault-Tolerant Systems","author":"O Maler","year":"2004","unstructured":"Maler, O., Nickovic, D.: Monitoring temporal properties of continuous signals. In: Lakhnech, Y., Yovine, S. (eds.) FORMATS\/FTRTFT -2004. LNCS, vol. 3253, pp. 152\u2013166. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-30206-3_12"},{"key":"12_CR17","unstructured":"Mania, H., Guy, A., Recht, B.: Simple random search of static linear policies is competitive for reinforcement learning. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 1805\u20131814 (2018)"},{"issue":"7540","key":"12_CR18","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_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1007\/978-3-030-59152-6_34","volume-title":"Automated Technology for Verification and Analysis","author":"D Ni\u010dkovi\u0107","year":"2020","unstructured":"Ni\u010dkovi\u0107, D., Yamaguchi, T.: RTAMT: online robustness monitors from STL. In: Hung, D.V., Sokolsky, O. (eds.) ATVA 2020. LNCS, vol. 12302, pp. 564\u2013571. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59152-6_34"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Peters, J., Mulling, K., Altun, Y.: Relative entropy policy search. In: Twenty-Fourth AAAI Conference on Artificial Intelligence (2010)","DOI":"10.1609\/aaai.v24i1.7727"},{"key":"12_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":"12_CR22","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"12_CR23","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, 484\u2013489 (2016)","journal-title":"Nature"},{"key":"12_CR24","doi-asserted-by":"publisher","first-page":"103535","DOI":"10.1016\/j.artint.2021.103535","volume":"299","author":"D Silver","year":"2021","unstructured":"Silver, D., Singh, S., Precup, D., Sutton, R.S.: Reward is enough. Artif. Intell. 299, 103535 (2021)","journal-title":"Artif. Intell."},{"issue":"7782","key":"12_CR25","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft ii using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"key":"12_CR26","first-page":"4555","volume":"44","author":"X Wang","year":"2021","unstructured":"Wang, X., Chen, Y., Zhu, W.: A survey on curriculum learning. IEEE Trans. Pattern Anal. Mach. Intell. 44, 4555\u20134576 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"12_CR27","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"issue":"7896","key":"12_CR28","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1038\/s41586-021-04357-7","volume":"602","author":"PR Wurman","year":"2022","unstructured":"Wurman, P.R., et al.: Outracing champion Gran Turismo drivers with deep reinforcement learning. Nature 602(7896), 223\u2013228 (2022)","journal-title":"Nature"}],"container-title":["Lecture Notes in Computer Science","Software Engineering and Formal Methods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-17108-6_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T17:04:46Z","timestamp":1710867886000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-17108-6_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031171079","9783031171086"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-17108-6_12","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":"1 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SEFM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Software Engineering and Formal Methods","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Berlin","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sefm2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sefm-conference.github.io\/2022\/","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":"39","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":"19","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":"9","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":"49% - 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":"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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}