{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T10:57:29Z","timestamp":1761562649113,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,9]],"date-time":"2020-06-09T00:00:00Z","timestamp":1591660800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,9]]},"DOI":"10.1145\/3394810.3394815","type":"proceedings-article","created":{"date-parts":[[2020,6,12]],"date-time":"2020-06-12T16:04:53Z","timestamp":1591977893000},"page":"149-160","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Adaptive Routing with Guaranteed Delay Bounds using Safe Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Gautham Nayak","family":"Seetanadi","sequence":"first","affiliation":[{"name":"Department of Automatic Control, Lund University, Lund, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karl-Erik","family":"\u00c5rz\u00e9n","sequence":"additional","affiliation":[{"name":"Department of Automatic Control, Lund University, Lund, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martina","family":"Maggio","sequence":"additional","affiliation":[{"name":"Department of Automatic Control, Lund University, Lund, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-247-2.50017-6"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2018.00012"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/2841997.2842006"},{"key":"e_1_3_2_1_5_1","first-page":"989","volume-title":"Proceedings of the 13th International Conference on Neural Information Processing Systems, NIPS'00","author":"Carlstr\u00f6m J.","year":"2000","unstructured":"J. Carlstr\u00f6m . Decomposition of reinforcement learning for admission control of self-similar call arrival processes . In Proceedings of the 13th International Conference on Neural Information Processing Systems, NIPS'00 , pages 989 -- 995 . MIT Press , 2000 . J. Carlstr\u00f6m. Decomposition of reinforcement learning for admission control of self-similar call arrival processes. In Proceedings of the 13th International Conference on Neural Information Processing Systems, NIPS'00, pages 989--995. MIT Press, 2000."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:MACH.0000039779.47329.3a"},{"key":"e_1_3_2_1_8_1","volume-title":"Safe exploration of state and action spaces in reinforcement learning. CoRR, abs\/1402.0560","author":"Garcia J.","year":"2014","unstructured":"J. Garcia and F. Fernandez . Safe exploration of state and action spaces in reinforcement learning. CoRR, abs\/1402.0560 , 2014 . J. Garcia and F. Fernandez. Safe exploration of state and action spaces in reinforcement learning. CoRR, abs\/1402.0560, 2014."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2886795"},{"key":"e_1_3_2_1_10_1","first-page":"11","volume-title":"Proceedings of the 7th Python in Science Conference","author":"Hagberg A. A.","year":"2008","unstructured":"A. A. Hagberg , D. A. Schult , and P. J. Swart . Exploring network structure, dynamics, and function using networkx. In G. Varoquaux, T. Vaught, and J. Millman, editors , Proceedings of the 7th Python in Science Conference , pages 11 -- 15 , Pasadena, CA USA , 2008 . A. A. Hagberg, D. A. Schult, and P. J. Swart. Exploring network structure, dynamics, and function using networkx. In G. Varoquaux, T. Vaught, and J. Millman, editors, Proceedings of the 7th Python in Science Conference, pages 11--15, Pasadena, CA USA, 2008."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/358172.358406"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/1404505"},{"key":"e_1_3_2_1_13_1","volume-title":"Reinforcement learning for adaptive routing. CoRR, abs\/cs\/0703138","author":"Peshkin L.","year":"2007","unstructured":"L. Peshkin and V. Savova . Reinforcement learning for adaptive routing. CoRR, abs\/cs\/0703138 , 2007 . L. Peshkin and V. Savova. Reinforcement learning for adaptive routing. CoRR, abs\/cs\/0703138, 2007."},{"key":"e_1_3_2_1_15_1","first-page":"903","volume-title":"Proceedings of the Seventeenth International Conference on Machine Learning, ICML '00","author":"Smart W. D.","year":"2000","unstructured":"W. D. Smart and L. P. Kaelbling . Practical reinforcement learning in continuous spaces . In Proceedings of the Seventeenth International Conference on Machine Learning, ICML '00 , pages 903 -- 910 , San Francisco, CA, USA , 2000 . Morgan Kaufmann Publishers Inc. W. D. Smart and L. P. Kaelbling. Practical reinforcement learning in continuous spaces. In Proceedings of the Seventeenth International Conference on Machine Learning, ICML '00, pages 903--910, San Francisco, CA, USA, 2000. Morgan Kaufmann Publishers Inc."},{"key":"e_1_3_2_1_16_1","volume-title":"Reinforcement learning: An Introduction. Adaptive computation and machine learning","author":"Sutton R. S.","year":"2018","unstructured":"R. S. Sutton and A. G. Barto . Reinforcement learning: An Introduction. Adaptive computation and machine learning . MIT Press , 2018 . R. S. Sutton and A. G. Barto. Reinforcement learning: An Introduction. Adaptive computation and machine learning. MIT Press, 2018."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509832"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"e_1_3_2_1_19_1","first-page":"1000","volume-title":"Proceedings of the 21st National Conference on Artificial Intelligence -","volume":"1","author":"Thomaz A. L.","year":"2006","unstructured":"A. L. Thomaz and C. Breazeal . Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance . In Proceedings of the 21st National Conference on Artificial Intelligence - Volume 1 , AAAI'06, pages 1000 -- 1005 . AAAI Press , 2006 . A. L. Thomaz and C. Breazeal. Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance. In Proceedings of the 21st National Conference on Artificial Intelligence - Volume 1, AAAI'06, pages 1000--1005. AAAI Press, 2006."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017924227920"},{"issue":"1","key":"e_1_3_2_1_21_1","first-page":"57","article-title":"\u00c1ngel Rodr\u00edguez Gonz\u00e1lez, and C. V. Regueiro. Learning on real robots from experience and simple user feedback","volume":"7","author":"Vidal P. Q.","year":"2013","unstructured":"P. Q. Vidal , R. I. Rodr\u00edguez , M . \u00c1ngel Rodr\u00edguez Gonz\u00e1lez, and C. V. Regueiro. Learning on real robots from experience and simple user feedback . Journal of Physical Agents , 7 ( 1 ): 57 -- 65 , 2013 . P. Q. Vidal, R. I. Rodr\u00edguez, M. \u00c1ngel Rodr\u00edguez Gonz\u00e1lez, and C. V. Regueiro. Learning on real robots from experience and simple user feedback. Journal of Physical Agents, 7(1):57--65, 2013.","journal-title":"Journal of Physical Agents"}],"event":{"name":"RTNS 2020: 28th International Conference on Real-Time Networks and Systems","sponsor":["INRIA INRIA Saclay \u00cele-de-France"],"location":"Paris France","acronym":"RTNS 2020"},"container-title":["Proceedings of the 28th International Conference on Real-Time Networks and Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394810.3394815","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394810.3394815","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:32:01Z","timestamp":1750195921000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394810.3394815"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,9]]},"references-count":20,"alternative-id":["10.1145\/3394810.3394815","10.1145\/3394810"],"URL":"https:\/\/doi.org\/10.1145\/3394810.3394815","relation":{},"subject":[],"published":{"date-parts":[[2020,6,9]]},"assertion":[{"value":"2020-06-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}