{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:09:25Z","timestamp":1783058965631,"version":"3.54.6"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Federal Ministry of Education and Research (BMBF)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10384208","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:36Z","timestamp":1705689516000},"page":"2135-2140","source":"Crossref","is-referenced-by-count":2,"title":["Deriving Rewards for Reinforcement Learning from Symbolic Behaviour Descriptions of Bipedal Walking"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Harnack","sequence":"first","affiliation":[{"name":"DFKI,Robotics Innovation Center,Bremen,Germany,28359"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph","family":"L\u00fcth","sequence":"additional","affiliation":[{"name":"Cyber-Physical Systems, DFKI,Bremen,Germany,28359"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lukas","family":"Gross","sequence":"additional","affiliation":[{"name":"DFKI,Robotics Innovation Center,Bremen,Germany,28359"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shivesh","family":"Kumar","sequence":"additional","affiliation":[{"name":"DFKI,Robotics Innovation Center,Bremen,Germany,28359"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank","family":"Kirchner","sequence":"additional","affiliation":[{"name":"DFKI,Robotics Innovation Center,Bremen,Germany,28359"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref2","volume-title":"Reinforcement learning and optimal control","author":"Bertsekas","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561814"},{"key":"ref4","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Rudin","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201397"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3066833"},{"key":"ref8","article-title":"A walk in the park: Learning to walk in 20 minutes with model-free reinforcement learning","author":"Smith","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref10","article-title":"Minimizing energy consumption leads to the emergence of gaits in legged robots","author":"Fu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"1939","article-title":"Learning to walk in 20 minutes","volume-title":"Proceedings of the Fourteenth Yale Workshop on Adaptive and Learning Systems","volume":"95585","author":"Tedrake"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref13","volume-title":"Gait Analysis","author":"Jaqueline","year":"1992"},{"key":"ref14","volume-title":"Compass-like biped robot part i: Stability and bifurcation of passive gaits","author":"Goswami","year":"1996"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)56086-3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TRA.2004.824685"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2005.847610"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-57318-6_30"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/lics.1996.561342"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"issue":"268","key":"ref21","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning im-plementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/humanoids47582.2021.9555770"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21401-6_36"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63588-0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12107"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","location":"Singapore, Singapore","start":{"date-parts":[[2023,12,13]]},"end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10384208.pdf?arnumber=10384208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:26:33Z","timestamp":1706027193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10384208\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10384208","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}