{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:18:38Z","timestamp":1756995518116,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":11,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T00:00:00Z","timestamp":1651622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,5,4]]},"DOI":"10.1145\/3501710.3524734","type":"proceedings-article","created":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T14:28:32Z","timestamp":1651156112000},"page":"1-2","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Poster Abstract: Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectives"],"prefix":"10.1145","author":[{"given":"Anand","family":"Balakrishnan","sequence":"first","affiliation":[{"name":"University of Southern California, United States"}]},{"given":"Stefan","family":"Jaksic","sequence":"additional","affiliation":[{"name":"AIT Austrian Institute of Technology GmbH, Austria"}]},{"given":"Edgar","family":"Aguilar","sequence":"additional","affiliation":[{"name":"AIT Austrian Institute of Technology GmbH, Austria"}]},{"given":"Dejan","family":"Nickovic","sequence":"additional","affiliation":[{"name":"AIT Austrian Institute of Technology GmbH, Austria"}]},{"given":"Jyotirmoy","family":"Deshmukh","sequence":"additional","affiliation":[{"name":"University of Southern California, United States"}]}],"member":"320","published-online":{"date-parts":[[2022,5,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Q-Learning for Robust Satisfaction of Signal Temporal Logic Specifications. In 2016 IEEE 55th Conference on Decision and Control (CDC). 6565\u20136570","author":"Aksaray Derya","year":"2016","unstructured":"Derya Aksaray , Austin Jones , Zhaodan Kong , Mac Schwager , and Calin Belta . 2016 . Q-Learning for Robust Satisfaction of Signal Temporal Logic Specifications. In 2016 IEEE 55th Conference on Decision and Control (CDC). 6565\u20136570 . https:\/\/doi.org\/10.1109\/cdc.2016.7799279 10.1109\/cdc.2016.7799279 Derya Aksaray, Austin Jones, Zhaodan Kong, Mac Schwager, and Calin Belta. 2016. Q-Learning for Robust Satisfaction of Signal Temporal Logic Specifications. In 2016 IEEE 55th Conference on Decision and Control (CDC). 6565\u20136570. https:\/\/doi.org\/10.1109\/cdc.2016.7799279"},{"key":"e_1_3_2_1_2_1","volume-title":"Concrete Problems in AI Safety. arXiv:1606.06565 [cs] (July","author":"Amodei Dario","year":"2016","unstructured":"Dario Amodei , Chris Olah , Jacob Steinhardt , Paul Christiano , John Schulman , and Dan Man\u00e9 . 2016. Concrete Problems in AI Safety. arXiv:1606.06565 [cs] (July 2016 ). arxiv:1606.06565\u00a0[cs] http:\/\/arxiv.org\/abs\/1606.06565 Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, and Dan Man\u00e9. 2016. Concrete Problems in AI Safety. arXiv:1606.06565 [cs] (July 2016). arxiv:1606.06565\u00a0[cs] http:\/\/arxiv.org\/abs\/1606.06565"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_3_1","DOI":"10.1109\/IROS40897.2019.8968254"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1109\/TSMC.1983.6313077"},{"volume-title":"The Power of Symbolic Automata and Transducers","author":"D\u2019Antoni Loris","unstructured":"Loris D\u2019Antoni and Margus Veanes . 2017. The Power of Symbolic Automata and Transducers . In Computer Aided Verification, Rupak Majumdar and Viktor Kun\u010dak (Eds.). Vol.\u00a010426. Springer International Publishing , Cham, 47\u201367. https:\/\/doi.org\/10.1007\/978-3-319-63387-9_3 10.1007\/978-3-319-63387-9_3 Loris D\u2019Antoni and Margus Veanes. 2017. The Power of Symbolic Automata and Transducers. In Computer Aided Verification, Rupak Majumdar and Viktor Kun\u010dak (Eds.). Vol.\u00a010426. Springer International Publishing, Cham, 47\u201367. https:\/\/doi.org\/10.1007\/978-3-319-63387-9_3","key":"e_1_3_2_1_5_1"},{"unstructured":"E.\u00a0M. Hahn M. Perez S. Schewe F. Somenzi A. Trivedi and D. Wojtczak. 2020. Reward Shaping for Reinforcement Learning with Omega- Regular Objectives. arXiv:2001.05977 [cs] (Jan. 2020). arxiv:2001.05977\u00a0[cs] http:\/\/arxiv.org\/abs\/2001.05977  E.\u00a0M. Hahn M. Perez S. Schewe F. Somenzi A. Trivedi and D. Wojtczak. 2020. Reward Shaping for Reinforcement Learning with Omega- Regular Objectives. arXiv:2001.05977 [cs] (Jan. 2020). arxiv:2001.05977\u00a0[cs] http:\/\/arxiv.org\/abs\/2001.05977","key":"e_1_3_2_1_6_1"},{"key":"e_1_3_2_1_7_1","volume-title":"Logically-Constrained Reinforcement Learning. arXiv:1801.08099 [cs] (Jan","author":"Hasanbeig Mohammadhosein","year":"2018","unstructured":"Mohammadhosein Hasanbeig , Alessandro Abate , and Daniel Kroening . 2018. Logically-Constrained Reinforcement Learning. arXiv:1801.08099 [cs] (Jan . 2018 ). arxiv:1801.08099\u00a0[cs] http:\/\/arxiv.org\/abs\/1801.08099 Mohammadhosein Hasanbeig, Alessandro Abate, and Daniel Kroening. 2018. Logically-Constrained Reinforcement Learning. arXiv:1801.08099 [cs] (Jan. 2018). arxiv:1801.08099\u00a0[cs] http:\/\/arxiv.org\/abs\/1801.08099"},{"key":"e_1_3_2_1_8_1","volume-title":"Formal Controller Synthesis for Continuous-Space MDPs via Model-Free Reinforcement Learning. arXiv:2003.00712 [cs, eess] (March","author":"Lavaei Abolfazl","year":"2020","unstructured":"Abolfazl Lavaei , Fabio Somenzi , Sadegh Soudjani , Ashutosh Trivedi , and Majid Zamani . 2020. Formal Controller Synthesis for Continuous-Space MDPs via Model-Free Reinforcement Learning. arXiv:2003.00712 [cs, eess] (March 2020 ), 98\u2013107. https:\/\/doi.org\/10.1109\/ICCPS48487.2020.00017 arxiv:2003.00712\u00a0[cs, eess] 10.1109\/ICCPS48487.2020.00017 Abolfazl Lavaei, Fabio Somenzi, Sadegh Soudjani, Ashutosh Trivedi, and Majid Zamani. 2020. Formal Controller Synthesis for Continuous-Space MDPs via Model-Free Reinforcement Learning. arXiv:2003.00712 [cs, eess] (March 2020), 98\u2013107. https:\/\/doi.org\/10.1109\/ICCPS48487.2020.00017 arxiv:2003.00712\u00a0[cs, eess]"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.1109\/CDC.2014.7039527"},{"volume-title":"Reinforcement learning: An introduction","author":"Sutton S","unstructured":"Richard\u00a0 S Sutton and Andrew\u00a0 G Barto . 2018. Reinforcement learning: An introduction ( second edition ed.). MIT press , Cambridge, Massachusetts . Richard\u00a0S Sutton and Andrew\u00a0G Barto. 2018. Reinforcement learning: An introduction(second edition ed.). MIT press, Cambridge, Massachusetts.","key":"e_1_3_2_1_10_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1007\/BF00992698"}],"event":{"sponsor":["SIGBED ACM Special Interest Group on Embedded Systems"],"acronym":"HSCC '22","name":"HSCC '22: 25th ACM International Conference on Hybrid Systems: Computation and Control","location":"Milan Italy"},"container-title":["25th ACM International Conference on Hybrid Systems: Computation and Control"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3501710.3524734","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3501710.3524734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:11Z","timestamp":1750183811000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3501710.3524734"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,4]]},"references-count":11,"alternative-id":["10.1145\/3501710.3524734","10.1145\/3501710"],"URL":"https:\/\/doi.org\/10.1145\/3501710.3524734","relation":{},"subject":[],"published":{"date-parts":[[2022,5,4]]},"assertion":[{"value":"2022-05-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}