{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T18:16:00Z","timestamp":1730225760394,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T00:00:00Z","timestamp":1669593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T00:00:00Z","timestamp":1669593600000},"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":[[2022,11,28]]},"DOI":"10.1109\/humanoids53995.2022.10000201","type":"proceedings-article","created":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T19:08:26Z","timestamp":1672945706000},"page":"350-357","source":"Crossref","is-referenced-by-count":1,"title":["End-To-End Deep Reinforcement Learning for First-Person Pedestrian Visual Navigation in Urban Environments"],"prefix":"10.1109","author":[{"given":"Honghu","family":"Xue","sequence":"first","affiliation":[{"name":"Institute for Robotics and Cognitive Systems, University of Luebeck,Luebeck"}]},{"given":"Rui","family":"Song","sequence":"additional","affiliation":[{"name":"Institute for Robotics and Cognitive Systems, University of Luebeck,Luebeck"}]},{"given":"Julian","family":"Petzold","sequence":"additional","affiliation":[{"name":"Institute of Computer Engineering, University of Luebeck,Luebeck"}]},{"given":"Benedikt","family":"Hein","sequence":"additional","affiliation":[{"name":"Institute of Automation Technology, Helmut Schmidt University,Ham-burg"}]},{"given":"Heiko","family":"Hamann","sequence":"additional","affiliation":[{"name":"Institute of Computer Engineering, University of Luebeck,Luebeck"}]},{"given":"Elmar","family":"Rueckert","sequence":"additional","affiliation":[{"name":"Chair of Cyber-Physical-Systems, Montanuniversität Leoben,Leoben"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3048662"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAR55106.2022.9782646"},{"key":"ref3","first-page":"407","article-title":"Discrete residual flow for probabilistic pedestrian behavior prediction","volume-title":"Conference on Robot Learning. PMLR","author":"Jain"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460655"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560962"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref7","first-page":"181:1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00255-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"article-title":"Dsac: Distributional soft actor critic for risk-sensitive reinforcement learning","volume-title":"Reinforcement Learning for Real Life Workshop at ICML","author":"Ma","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2019.8870964"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-70139-4","article-title":"Infogail: Interpretable imitation learning from visual demonstrations","volume":"30","author":"Li","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICNSC48988.2020.9238090"},{"key":"ref16","first-page":"482","article-title":"Re-verse curriculum generation for reinforcement learning","volume-title":"Conference on robot learning. PMLR","author":"Florensa"},{"article-title":"Automated curriculum generation through setter-solver interactions","volume-title":"International conference on learning representations","author":"Racaniere","key":"ref17"},{"key":"ref18","first-page":"1515","article-title":"Automatic goal generation for reinforcement learning agents","volume-title":"International conference on machine learning. PMLR","author":"Florensa"},{"key":"ref19","article-title":"Hind-sight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Recurrent experience replay in distributed reinforcement learning","volume-title":"International conference on learning representations","author":"Kapturowski","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","volume-title":"International Conference on Learning Representations (ICLR) Workshop","author":"Bai","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/app12063153"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123451"},{"key":"ref25","article-title":"A simple neural attentive meta-learner","author":"Mishra","year":"2017","journal-title":"arXiv preprint"},{"key":"ref26","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"International conference on machine learning. PMLR","author":"Dabney"},{"key":"ref27","article-title":"Fully param-eterized quantile function for distributional reinforcement learning","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"3455","article-title":"Non-decreasing quantile function network with efficient exploration for distributional reinforcement learning","volume-title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21","volume":"8","author":"Zhou","year":"2021"},{"key":"ref30","article-title":"Observe and look further: Achieving consistent performance on atari","author":"Pohlen","year":"2018","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Prioritized experience replay","volume-title":"International Conference on Learning Representations","volume":"2016","author":"Schaul"},{"key":"ref32","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on Robot Learning. PMLR","author":"Dosovitskiy"}],"event":{"name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","start":{"date-parts":[[2022,11,28]]},"location":"Ginowan, Japan","end":{"date-parts":[[2022,11,30]]}},"container-title":["2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9999736\/9999739\/10000201.pdf?arnumber=10000201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T13:45:15Z","timestamp":1709387115000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10000201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,28]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/humanoids53995.2022.10000201","relation":{},"subject":[],"published":{"date-parts":[[2022,11,28]]}}}