{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:53:13Z","timestamp":1763193193234,"version":"3.45.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228766","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Causality-Guided Policy Optimization in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Lishan","family":"Yang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuju","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihua","family":"Liu","sequence":"additional","affiliation":[{"name":"Laboratory for Big Data and Decision, National University of Defence Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibin","family":"Zhan","sequence":"additional","affiliation":[{"name":"JD Explore Academy,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2019.05.029"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/820"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3331728"},{"key":"ref7","first-page":"20 064","article-title":"Causality-driven hierarchical structure discovery for reinforcement learning","volume":"35","author":"Hu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Pretraining deep actor-critic reinforcement learning algorithms with expert demonstrations","year":"2018","author":"Zhang","key":"ref8"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.fmre.2021.09.003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.12.019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3202244"},{"key":"ref14","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"article-title":"Causal reinforcement learning: A survey","year":"2023","author":"Deng","key":"ref16"},{"key":"ref17","article-title":"Bandits with unobserved confounders: A causal approach","volume":"28","author":"Bareinboim","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"8605","article-title":"Generalization bounds for estimating causal effects of continuous treatments","volume":"35","author":"Wang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Elements of causal inference: foundations and learning algorithms.","year":"2017","author":"Peters","key":"ref19"},{"issue":"2","key":"ref20","first-page":"3","article-title":"Models, reasoning and inference","volume":"19","author":"Pearl","year":"2000","journal-title":"Cambridge, UK: CambridgeUniversityPress"},{"key":"ref21","first-page":"21 164","article-title":"Provably efficient causal reinforcement learning with confounded observational data","volume":"34","author":"Wang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Woulda, coulda, shoulda: Counterfactually-guided policy search","year":"2018","author":"Buesing","key":"ref22"},{"article-title":"Causal reinforcement learning","volume-title":"NeurIPS 2018 Workshop on","author":"Bareinboim","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25123-3"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228766.pdf?arnumber=11228766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:49:23Z","timestamp":1763192963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228766\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228766","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}