{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:04:10Z","timestamp":1783530250243,"version":"3.55.0"},"reference-count":120,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2309760"],"award-info":[{"award-number":["2309760"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2317117"],"award-info":[{"award-number":["2317117"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tai.2023.3311428","type":"journal-article","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T14:31:10Z","timestamp":1693837870000},"page":"1939-1953","source":"Crossref","is-referenced-by-count":47,"title":["Neurosymbolic Reinforcement Learning and Planning: A Survey"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9712-0265","authenticated-orcid":false,"given":"Kamal","family":"Acharya","sequence":"first","affiliation":[{"name":"Department of Information Systems, University of Maryland, Baltimore County, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4142-3195","authenticated-orcid":false,"given":"Waleed","family":"Raza","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Embry-Riddle Aeronautical University, Daytona Beach, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5137-1018","authenticated-orcid":false,"given":"Carlos","family":"Dourado","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Embry-Riddle Aeronautical University, Daytona Beach, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6757-105X","authenticated-orcid":false,"given":"Alvaro","family":"Velasquez","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Colorado, Boulder, CO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2631-9223","authenticated-orcid":false,"given":"Houbing Herbert","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Information Systems, University of Maryland, Baltimore County, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref3","article-title":"An introduction of mini-alphastar","author":"Liu","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3233\/faia210348"},{"key":"ref5","article-title":"Towards data-and knowledge-driven artificial intelligence: A survey on neuro-symbolic computing","author":"Wang","year":"2022"},{"key":"ref6","article-title":"A survey on neural-symbolic systems","author":"Yu","year":"2021"},{"key":"ref7","article-title":"Survey on applications of neurosymbolic artificial intelligence","author":"Bouneffouf","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref9","article-title":"Deep reinforcement learning: An overview","author":"Li","year":"2017"},{"key":"ref10","article-title":"A survey on causal reinforcement learning","author":"Zeng","year":"2023"},{"issue":"1","key":"ref11","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garca","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3040957"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3459991"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/app11114948"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10205-5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/880"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2019.8917870"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF02478259"},{"key":"ref24","article-title":"On the origin of deep learning","author":"Wang","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1949.10483310"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.43.8.749"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref28","article-title":"The perceptron, A perceiving and recognizing automaton project para","author":"Rosenblatt","year":"1957"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1147\/rd.33.0210"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1971.4308320"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3618-5_3"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref38","article-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref39","volume-title":"Reinforcement Learning for Robots Using Neural Networks","author":"Lin","year":"1992"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.31"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref42","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref43","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref46","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref47","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref48","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref49","first-page":"4572","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2016"},{"key":"ref50","article-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref51","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref52","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc., Int. Conf. Mach. Learn.","author":"Bellemare","year":"2017"},{"key":"ref53","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref57","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref58","article-title":"QT-Opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"Kalashnikov","year":"2018"},{"key":"ref59","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Espeholt","year":"2018"},{"key":"ref60","article-title":"Mastering chess and Shogi by self-play with a general reinforcement learning algorithm","author":"Silver","year":"2017"},{"key":"ref61","article-title":"AlphaStar: Mastering the real-time strategy game StarCraft II","year":"2019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05172-4"},{"key":"ref64","first-page":"3008","article-title":"Learning to summarize with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Stiennon","year":"2020"},{"key":"ref65","article-title":"The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","author":"Mao","year":"2019"},{"key":"ref66","volume-title":"Thinking, Fast and Slow","author":"Kahneman","year":"2011"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i17.17765"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10448-w"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/679"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3233\/AIC-210084"},{"key":"ref71","article-title":"Dimensions of neural-symbolic integrationA structured survey","author":"Bader","year":"2005"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v43i1.19122"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-33-4859-2_29"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1049\/cmu2.12447"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1080.0305"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.1900533"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3616864"},{"key":"ref78","article-title":"A survey on intrinsic motivation in reinforcement learning","author":"Aubret","year":"2019"},{"key":"ref79","article-title":"A survey on deep reinforcement learning-based approaches for adaptation and generalization","author":"Yadav","year":"2022"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/s0927-0507(05)80172-0"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103852"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3508546.3508598"},{"key":"ref83","article-title":"A deep reinforced model for abstractive summarization","author":"Paulus","year":"2017"},{"key":"ref84","article-title":"Towards deep symbolic reinforcement learning","author":"Garnelo","year":"2016"},{"key":"ref85","article-title":"Towards symbolic reinforcement learning with common sense","author":"Garcez","year":"2018"},{"key":"ref86","article-title":"Learning symbolic rules for interpretable deep reinforcement learning","author":"Ma","year":"2021"},{"key":"ref87","first-page":"5979","article-title":"Discovering symbolic policies with deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Landajuela","year":"2021"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06142-7"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20663"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.283"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1060"},{"key":"ref92","article-title":"Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning","author":"Das","year":"2017"},{"key":"ref93","first-page":"2499","article-title":"Verifiable reinforcement learning via policy extraction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bastani","year":"2018"},{"key":"ref94","first-page":"6172","article-title":"Neurosymbolic reinforcement learning with formally verified exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Anderson","year":"2020"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17427"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v32i1.19854"},{"key":"ref97","first-page":"732","article-title":"Translating omega-regular specifications to average objectives for model-free reinforcement learning","volume-title":"Proc. 21st Int. Conf. Auton. Agents Multiagent Syst.","author":"Kazemi","year":"2022"},{"key":"ref98","article-title":"Imitation-projected programmatic reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Verma","year":"2019"},{"key":"ref99","first-page":"5045","article-title":"Programmatically interpretable reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma","year":"2018"},{"key":"ref100","first-page":"1","article-title":"Synthesizing programmatic policies that inductively generalize","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Inala","year":"2020"},{"key":"ref101","first-page":"25146","article-title":"Learning to synthesize programs as interpretable and generalizable policies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Trivedi","year":"2021"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16935"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16638"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012970"},{"key":"ref105","article-title":"Causal discovery with reinforcement learning","author":"Zhu","year":"2019"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1561\/2300000021"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2007.339624"},{"key":"ref108","first-page":"21","article-title":"Neuro-symbolic program search for autonomous driving decision module design","volume-title":"Proc. Conf. Robot Learn.","author":"Sun","year":"2021"},{"key":"ref109","article-title":"Learning neuro-symbolic skills for bilevel planning","author":"Silver","year":"2022"},{"key":"ref110","article-title":"CausalWorld: A robotic manipulation benchmark for causal structure and transfer learning","author":"Ahmed","year":"2020"},{"key":"ref111","first-page":"12333","article-title":"DouZero: Mastering DouDizhu with self-play deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zha","year":"2021"},{"key":"ref112","first-page":"582","article-title":"Knowledge graph construction techniques","volume":"53","author":"Yang","year":"2016","journal-title":"J. Comput. Res. Develop."},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.07.017"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3070843"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS48487.2020.00012"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/PDMC-HiBi.2010.9"},{"key":"ref117","first-page":"1","article-title":"The SMT-LIB standard: Version 2.0","volume-title":"Proc. 8th Int. Workshop Satisfiability Modulo Theories","author":"Barrett","year":"2010"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1561\/2500000049"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(90)90087-6"},{"key":"ref120","first-page":"1598","article-title":"Learning to connect language and perception","volume-title":"Proc. 23rd Nat. Conf. Artif. Intell.","author":"Mooney","year":"2008"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9078688\/10532210\/10238788-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10532210\/10238788.pdf?arnumber=10238788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:08:57Z","timestamp":1755911337000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10238788\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":120,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tai.2023.3311428","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}