{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T13:26:40Z","timestamp":1775482000321,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,19]],"date-time":"2020-10-19T00:00:00Z","timestamp":1603065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,19]],"date-time":"2020-10-19T00:00:00Z","timestamp":1603065600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,19]],"date-time":"2020-10-19T00:00:00Z","timestamp":1603065600000},"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":[[2020,10,19]]},"DOI":"10.1109\/iv47402.2020.9304738","type":"proceedings-article","created":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T07:14:14Z","timestamp":1610262854000},"page":"1589-1594","source":"Crossref","is-referenced-by-count":31,"title":["Graph Neural Networks and Reinforcement Learning for Behavior Generation in Semantic Environments"],"prefix":"10.1109","author":[{"given":"Patrick","family":"Hart","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1889","article-title":"Trust Region Policy Optimization","author":"schulman","year":"0","journal-title":"Proceedings of The 32nd International Conference on Machine Learning"},{"key":"ref11","article-title":"Proximal Policy Optimization Algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref12","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"4th International Conference on Learning Representations"},{"key":"ref13","article-title":"Maximum a Posteriori Policy Optimisation","author":"abdolmaleki","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref14","first-page":"1856","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","volume":"80","author":"haarnoja","year":"0","journal-title":"Machine Learning Research"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968560"},{"key":"ref17","article-title":"NerveNet: Learning Structured Policy with Graph Neural Networks","author":"wang","year":"2018","journal-title":"6th International Conference on Learning Representations ICLR 2018"},{"key":"ref18","author":"sanchez-gonzalez","year":"2018","journal-title":"Graph networks as learnable physics engines for inference and control"},{"key":"ref19","first-page":"6348","article-title":"Learning combinatorial optimization algorithms over graphs","author":"khalil","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref3","article-title":"Dynamic Interaction-Aware Scene Understanding for Reinforcement Learning in Autonomous Driving","volume":"abs 1909 13582","author":"h\u00fcgle","year":"2019","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1026"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01175"},{"key":"ref8","article-title":"Relational inductive biases, deep learning, and graph networks","volume":"abs 1806 1261","author":"battaglia","year":"2018","journal-title":"CoRR"},{"key":"ref7","author":"bruna","year":"2013","journal-title":"Spectral networks and locally connected networks on graphs"},{"key":"ref2","first-page":"211","article-title":"Learning Continuous Muscle Control for a Multi-joint Arm by Extending Proximal Policy Optimization with a Liquid State Machine","author":"camilo","year":"2018","journal-title":"Artificial Neural Networks and Machine Learning - ICANN 2018 — 27th International Conference on Artificial Neural Networks"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/RoMoCo.2019.8787360"},{"key":"ref9","volume":"258","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","author":"bernhard","year":"2020","journal-title":"BARK Open Behavior Benchmarking in Multi-Agent Environments"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500363"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32460-4"}],"event":{"name":"2020 IEEE Intelligent Vehicles Symposium (IV)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2020,10,19]]},"end":{"date-parts":[[2020,11,13]]}},"container-title":["2020 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9304518\/9304528\/09304738.pdf?arnumber=9304738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:57:59Z","timestamp":1656453479000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9304738\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,19]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/iv47402.2020.9304738","relation":{},"subject":[],"published":{"date-parts":[[2020,10,19]]}}}