{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T13:27:25Z","timestamp":1768310845725,"version":"3.49.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"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":[[2025,12,9]]},"DOI":"10.1109\/cdc57313.2025.11312735","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:19:56Z","timestamp":1768241996000},"page":"3127-3134","source":"Crossref","is-referenced-by-count":0,"title":["Using Control Barrier Functions for Constrained Reinforcement Learning in Backward Chained Behavior Trees"],"prefix":"10.1109","author":[{"given":"Mart","family":"Karta\u0161ev","sequence":"first","affiliation":[{"name":"Royal Institute of Technology (KTH),Robotics, Perception and Learning Lab., School of Electrical Engineering and Computer Science,Stockholm,Sweden,SE-100 44"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jannik","family":"Wagner","sequence":"additional","affiliation":[{"name":"Royal Institute of Technology (KTH),Robotics, Perception and Learning Lab., School of Electrical Engineering and Computer Science,Stockholm,Sweden,SE-100 44"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petter","family":"\u00d6gren","sequence":"additional","affiliation":[{"name":"Royal Institute of Technology (KTH),Robotics, Perception and Learning Lab., School of Electrical Engineering and Computer Science,Stockholm,Sweden,SE-100 44"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104096"},{"key":"ref2","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref3","first-page":"3420","article-title":"Control Barrier Functions: Theory and Applications","volume-title":"2019 18th European Control Conference (ECC)","author":"Ames"},{"key":"ref4","article-title":"Modularity and Design in Reactive Intelligence","author":"Bryson","year":"2001"},{"key":"ref5","first-page":"4","article-title":"Fac\u00b8ade: An experiment in building a fully-realized interactive drama","volume-title":"Game developers conference","volume":"2","author":"Mateas"},{"key":"ref6","article-title":"Understanding Behavior Trees | AiGameDev.com","author":"Champandard","year":"2007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3511606"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref10","article-title":"A framework for constrained and adaptive behavior-based agents","author":"Pereira","year":"2015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-01326-7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3216996"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-071723-102940"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304151"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794128"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010747"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342319"},{"key":"ref18","first-page":"12","article-title":"A proposal for combining reinforcement learning and behavior trees for regression testing over gameplay metrics","author":"Gutierrez-Sanchez","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2013.6633623"},{"key":"ref20","article-title":"Simulation results on selector adaptation in behavior trees","author":"Hannaford","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.2991\/essaeme-16.2016.120"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICSAI.2017.8248348"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref24","article-title":"On the Fly Adaptation of Behavior Tree-Based Policies through Reinforcement Learning","author":"Iannotta","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794107"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561853"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1201\/9780429489105"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1201\/9780429489105"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2514\/6.2006-6197"},{"key":"ref31","article-title":"A closer look at invalid action masking in policy gradient algorithms","volume-title":"The International FLAIRS Conference Proceedings","volume":"35","author":"Huang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3382477"},{"key":"ref33","article-title":"Unity: A general platform for intelligent agents","author":"Juliani","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430929"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127277"},{"key":"ref37","first-page":"834","article-title":"Improving stochastic policy gradients in continuous control with deep reinforcement learning using the beta distribution","volume-title":"Proceedings of the 34th International Conference on Machine Learning - Volume 70","author":"Chou"},{"key":"ref38","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proceedings of the 34th International Conference on Machine Learning - Volume 70","author":"Achiam"}],"event":{"name":"2025 IEEE 64th Conference on Decision and Control (CDC)","location":"Rio de Janeiro, Brazil","start":{"date-parts":[[2025,12,9]]},"end":{"date-parts":[[2025,12,12]]}},"container-title":["2025 IEEE 64th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11311984\/11311968\/11312735.pdf?arnumber=11312735","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:14:17Z","timestamp":1768292057000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11312735\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/cdc57313.2025.11312735","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]}}}