{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:02:20Z","timestamp":1755993740829,"version":"3.44.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tai.2024.3453230","type":"journal-article","created":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T13:44:34Z","timestamp":1725371074000},"page":"6186-6195","source":"Crossref","is-referenced-by-count":0,"title":["Q-Cogni: An Integrated Causal Reinforcement Learning Framework"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2301-6289","authenticated-orcid":false,"given":"Cristiano","family":"da Costa Cunha","sequence":"first","affiliation":[{"name":"Department of Computer Science and Software Engineering, University of Western Australia, Perth, WA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7409-0948","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, University of Western Australia, Perth, WA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0748-8040","authenticated-orcid":false,"given":"Tim","family":"French","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, University of Western Australia, Perth, WA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5206-3842","authenticated-orcid":false,"given":"Ajmal","family":"Mian","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, University of Western Australia, Perth, WA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780199399550.013.20"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0197-y"},{"article-title":"Woulda, coulda, shoulda: Counterfactually-guided policy search","year":"2018","author":"Buesing","key":"ref3"},{"article-title":"Causal reasoning from meta-reinforcement learning","year":"2019","author":"Dasgupta","key":"ref4"},{"article-title":"Causal reinforcement learning using observational and interventional data","year":"2021","author":"Gasse","key":"ref5"},{"key":"ref6","first-page":"1809","article-title":"Schema networks: Zero-shot transfer with a generative causal model of intuitive physics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kansky","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5631"},{"key":"ref8","first-page":"95","article-title":"Causal based Q-learning","volume":"149","author":"Molina","year":"2020","journal-title":"Res. Comput. Sci."},{"key":"ref9","first-page":"421","article-title":"Causal discovery and reinforcement learning: A synergistic integration","volume-title":"Proc. Int. Conf. Probabilistic Graphical Models","author":"M\u00e9ndez-Molina","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718515.ch1"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"article-title":"OpenAI gym","year":"2016","author":"Brockman","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tssc.1968.300136"},{"article-title":"NYC TLC","year":"2022","author":"Taxi","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3271625"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2200\/s00832ed1v01y201802aim037"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"article-title":"Deep learning: A critical appraisal","year":"2018","author":"Marcus","key":"ref20"},{"key":"ref21","first-page":"39","article-title":"Causal inference","volume-title":"Proc. Causality: Objectives Assessment","author":"Pearl","year":"2010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SIU.2019.8806389"},{"article-title":"Causal reinforcement learning: A primer","year":"2020","author":"John","key":"ref25"},{"article-title":"Causality and batch reinforcement learning: Complementary approaches to planning in unknown domains","year":"2020","author":"Bannon","key":"ref26"},{"key":"ref27","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"32","author":"Janner","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref29","first-page":"22905","article-title":"Causal influence detection for improving efficiency in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Seitzer","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20862"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.08.016"},{"article-title":"Causal discovery with reinforcement learning","year":"2019","author":"Zhu","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/491"},{"author":"Huang","key":"ref34","article-title":"Causal discovery from incomplete data using an encoder and reinforcement learning"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.06.028"},{"article-title":"A meta-reinforcement learning algorithm for causal discovery","year":"2022","author":"Sauter","key":"ref36"},{"article-title":"Sample-efficient reinforcement learning via counterfactual-based data augmentation","year":"2020","author":"Lu","key":"ref37"},{"key":"ref38","first-page":"526","article-title":"Efficient reinforcement learning with prior causal knowledge","volume-title":"Proc. Conf. Causal Learn. Reasoning","author":"Lu","year":"2022"},{"key":"ref39","first-page":"9492","article-title":"DAGs with NO TEARS: Continuous optimization for structure learning","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Zheng","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2015.12.007"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.14482\/inde.34.2.8180"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0121087"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA51294.2020.00013"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511921735"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref46","first-page":"3053","article-title":"RLlib: Abstractions for distributed reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang","year":"2018"},{"article-title":"CausalNex","year":"2021","author":"Beaumont","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.compenvurbsys.2017.05.004"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/10794552\/10663687.pdf?arnumber=10663687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:34Z","timestamp":1755911374000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10663687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":48,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3453230","relation":{},"ISSN":["2691-4581"],"issn-type":[{"type":"electronic","value":"2691-4581"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}