{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:17:18Z","timestamp":1783059438525,"version":"3.54.6"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"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":[[2026,3,16]]},"DOI":"10.1109\/percomworkshops68308.2026.11585246","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T19:42:40Z","timestamp":1783021360000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Causal Models Improve Reinforcement Learning for Pervasive and Robotic Tasks"],"prefix":"10.1109","author":[{"given":"Giovanni","family":"Briglia","sequence":"first","affiliation":[{"name":"Università di Modena e Reggio Emilia,Dipartimento di Scienze e Metodi Dell’Ingegneria,Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Mariani","sequence":"additional","affiliation":[{"name":"Università di Modena e Reggio Emilia,Dipartimento di Scienze e Metodi Dell’Ingegneria,Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franco","family":"Zambonelli","sequence":"additional","affiliation":[{"name":"Università di Modena e Reggio Emilia,Dipartimento di Scienze e Metodi Dell’Ingegneria,Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i27.35095"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-021-00398-z"},{"key":"ref4","first-page":"5739","article-title":"Towards sample efficient reinforcement learning","volume-title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI","author":"Yu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref6","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Cobbe"},{"key":"ref7","first-page":"1425","article-title":"Context-aware deep reinforcement learning for autonomous robotic navigation in unknown area","volume-title":"Conference on Robot Learning, CoRL","volume":"229","author":"Liang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-13562-9_40"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3403001"},{"key":"ref11","article-title":"Generalizability in causal reinforcement learning","author":"Bareinboim","year":"2020","journal-title":"ACM Transactions on Machine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-08049-3_4"},{"key":"ref13","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Advances in Neural Information Processing Systems 12, NIPS","author":"Konda","year":"1999"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref15","article-title":"ACE: off-policy actor-critic with causality-aware entropy regularization","volume-title":"Forty-first International Conference on Machine Learning, ICML","author":"Ji"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/S0927-0507(05)80172-0","article-title":"Markov decision processes","volume":"2","author":"Puterman","year":"1990","journal-title":"Handbooks in operations research and management science"},{"key":"ref17","first-page":"1471","article-title":"Variance reduction tech-niques for gradient estimates in reinforcement learning","volume":"5","author":"Greensmith","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"ref18","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML","volume":"80","author":"Fujimoto"},{"key":"ref19","volume-title":"Elements of causal inference: foundations and learning algorithms","author":"Peters","year":"2017"},{"key":"ref20","volume-title":"The book of why: the new science of cause and effect","author":"Pearl","year":"2018"},{"key":"ref21","article-title":"When should reinforcement learning use causal reasoning?","volume":"2025","author":"Schulte","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref22","author":"Pearl","year":"1989","journal-title":"Probabilistic reasoning in intelligent systems - networks of plausible inference"},{"key":"ref23","first-page":"6","article-title":"pgmpy: Probabilistic graphical models using python","volume-title":"Proceedings of the 14th Python in Science Conference 2015 (SciPy)","author":"Ankan"},{"key":"ref24","first-page":"147:1","article-title":"Dowhy-gcm: An extension of dowhy for causal inference in graphical causal models","volume":"25","author":"Bl\u00f6baum","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0398"},{"key":"ref26","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proceedings of the 33nd International Conference on Machine Learning, ICML","volume":"48","author":"Mnih"},{"key":"ref27","first-page":"29 304","article-title":"Deep reinforcement learning at the edge of the statistical precipice","author":"Agarwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","first-page":"246","article-title":"Learning by doing: Controlling a dynamical system using causality, control, and reinforcement learning","volume-title":"NeurIPS 2021 Competitions and Demonstrations Track","volume":"176","author":"Weichwald","year":"2021"},{"key":"ref29","article-title":"Causalworld: A robotic manipulation benchmark for causal structure and transfer learning","volume-title":"9th International Conference on Learning Representations, ICLR","author":"Ahmed"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISC260477.2024.11004233"},{"key":"ref31","first-page":"2229","volume-title":"SCALE: causal learning and discovery of robot manipulation skills using simulation","volume":"229","author":"Lee","year":"2023"},{"key":"ref32","article-title":"Causality-based reinforcement learning method for multi-stage robotic tasks","volume":"abs\/2503.03145","author":"Deng","year":"2025","journal-title":"CoRR"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/978-3-031-77367-9_20","article-title":"Improving reinforcement learning-based autonomous agents with causal models","volume-title":"PRIMA 2024: Principles and Practice of Multi-Agent Systems","volume":"15395","author":"Briglia","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29198"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5631"},{"key":"ref36","article-title":"Causal policy learning in reinforcement learning: Backdoor-adjusted soft actor-critic","volume":"abs\/2506.05445","author":"Vo","year":"2025","journal-title":"CoRR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref38","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, ICML","volume":"37","author":"Schulman"},{"issue":"1","key":"ref39","first-page":"3","article-title":"Causal discovery and inference: concepts and recent methodological advances","volume-title":"Applied informatics","volume":"3","author":"Spirtes","year":"2016"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5220\/0013400100003896"}],"event":{"name":"2026 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)","location":"Pisa, Italy","start":{"date-parts":[[2026,3,16]]},"end":{"date-parts":[[2026,3,20]]}},"container-title":["2026 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11585185\/11585186\/11585246.pdf?arnumber=11585246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:29:19Z","timestamp":1783056559000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11585246\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/percomworkshops68308.2026.11585246","relation":{},"subject":[],"published":{"date-parts":[[2026,3,16]]}}}