{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:22:55Z","timestamp":1780053775953,"version":"3.54.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,14]]},"DOI":"10.1109\/cdc45484.2021.9683634","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T20:50:18Z","timestamp":1643748618000},"page":"6560-6565","source":"Crossref","is-referenced-by-count":3,"title":["Model-Free Learning of Safe yet Effective Controllers"],"prefix":"10.1109","author":[{"given":"Alper Kamil","family":"Bozkurt","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miroslav","family":"Pajic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Safe reinforcement learning via shielding","volume":"32","author":"alshiekh","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-25540-4_36"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.039"},{"key":"ref13","first-page":"2107","article-title":"Using reward machines for high-level task specification and decomposition in reinforcement learning","author":"icarte","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17462-0_27"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196796"},{"key":"ref16","article-title":"Temporal logic guided safe reinforcement learning using control barrier functions","author":"li","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636598"},{"key":"ref18","article-title":"Learning-based mean-payoff optimization in an unknown MDP under omega-regular constraints","author":"k?et\u00ednsk\u00fd","year":"2018","journal-title":"International Conference on Concurrency Theory"},{"key":"ref19","first-page":"583","article-title":"Multi-agent reinforcement learning with temporal logic specifications","author":"hammond","year":"2021","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3233\/AIC-150682"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2009.2030225"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcon.2016.04.009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3987"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-53291-8_21"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3309683"},{"key":"ref2","author":"baier","year":"2008","journal-title":"Principles of Model Checking"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","article-title":"Synthesis of discounted-reward optimal policies for Markov decision processes under linear temporal logic specifications","author":"kalagarla","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41540-6_17"},{"key":"ref22","first-page":"197","article-title":"Multi-criteria reinforcement learning","author":"g\u00e1bor","year":"1998","journal-title":"Int Conf on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011254632723"},{"key":"ref24","article-title":"Learning optimal strategies for temporal tasks in stochastic games","author":"bozkurt","year":"2021"},{"key":"ref23","article-title":"Modelfree reinforcement learning for stochastic games with linear temporal logic objectives","author":"bozkurt","year":"2021","journal-title":"IEEE International Conference on Robotics and Automation (ICRA)"}],"event":{"name":"2021 60th IEEE Conference on Decision and Control (CDC)","location":"Austin, TX, USA","start":{"date-parts":[[2021,12,14]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 60th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9682670\/9682776\/09683634.pdf?arnumber=9683634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:57:57Z","timestamp":1652201877000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9683634\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9683634","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}