{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T15:07:23Z","timestamp":1768316843013,"version":"3.49.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342319","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"1572-1579","source":"Crossref","is-referenced-by-count":3,"title":["Improving the Performance of Backward Chained Behavior Trees that use Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Mart","family":"Kartasev","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Royal Institute of Technology (KTH),Robotics, Perception and Learning Lab.,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin","family":"Sal\u00e9r","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Royal Institute of Technology (KTH),Robotics, Perception and Learning Lab.,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petter","family":"\u00d6gren","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Royal Institute of Technology (KTH),Robotics, Perception and Learning Lab.,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3511606"},{"key":"ref3","first-page":"4","article-title":"Facade: An experiment in building a fully-realized interactive drama","volume-title":"Game developers conference","volume":"2","author":"Mateas"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010747"},{"key":"ref5","article-title":"A framework for constrained and adaptive behavior-based agents","author":"Pereira","year":"2015","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2013.6633623"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2991\/essaeme-16.2016.120"},{"key":"ref8","article-title":"Simulation results on selector adaptation in behavior trees","author":"Hannaford","year":"2016","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992501"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICSAI.2017.8248348"},{"key":"ref11","article-title":"Improving the performance of learned controllers in behavior trees using value function estimates at switching boundaries","author":"Karta\u0161ev","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12239-2_11"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2016.2543661"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2816806"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICECCS.2019.00026"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636292"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3174258"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794128"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104096"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1201\/9780429489105"},{"key":"ref21","first-page":"4246","article-title":"The malmo plat-form for artificial intelligence experimentation","volume-title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","author":"Johnson"},{"key":"ref22","volume-title":"Stable baselines3","author":"Raffin","year":"2019"},{"key":"ref23","volume-title":"Repository: Improving the performance of backward chainedbehavior trees using reinforcement learning","author":"Kartasev","year":"2023"},{"key":"ref24","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv preprint"},{"key":"ref25","volume-title":"Openai baselines","author":"Dhariwal","year":"2017"},{"key":"ref26","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref27","author":"Mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref28","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, ser. ICML16. JMLR.org","author":"Mnih"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342319.pdf?arnumber=10342319","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:28:45Z","timestamp":1703014125000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342319\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342319","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}