{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T17:56:12Z","timestamp":1762019772468,"version":"build-2065373602"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/robio49542.2019.8961480","type":"proceedings-article","created":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T14:49:51Z","timestamp":1579618191000},"page":"2092-2098","source":"Crossref","is-referenced-by-count":3,"title":["Learning Adaptive Driving Behavior Using Recurrent Deterministic Policy Gradients"],"prefix":"10.1109","author":[{"given":"Kaustubh","family":"Mani","sequence":"first","affiliation":[{"name":"IIIT-Hyderabad,Robotics Research Center"}]},{"given":"Meha","family":"Kaushik","sequence":"additional","affiliation":[{"name":"Microsoft Canada Development Center"}]},{"given":"Nirvan","family":"Singhania","sequence":"additional","affiliation":[{"name":"IIIT-Hyderabad,Robotics Research Center"}]},{"given":"K. Madhava","family":"Krishna","sequence":"additional","affiliation":[{"name":"IIIT-Hyderabad,Robotics Research Center"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"ICML"},{"key":"ref11","article-title":"End-to-end deep reinforcement learning for lane keeping assist","author":"sallab","year":"2016","journal-title":"NIPS Workshop on Machine Learning for Intelligent Transportation Systems (MLITS)"},{"key":"ref12","article-title":"Learning to drive in a day","author":"kendall","year":"2018","journal-title":"arXiv preprint arXiv 1807 00412"},{"key":"ref13","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"article-title":"TORCS, The Open Racing Car Simulator","year":"2014","author":"wymann","key":"ref14"},{"key":"ref15","article-title":"Airsim: High-fidelity visual and physical simulation for autonomous vehicles","author":"shah","year":"2017","journal-title":"Field and Service Robotics"},{"key":"ref16","first-page":"1","article-title":"CARLA: An open urban driving simulator","author":"dosovitskiy","year":"2017","journal-title":"Proceedings of the 1st Annual Conference on Robot Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2011.940472"},{"key":"ref3","article-title":"On a formal model of safe and scalable self-driving cars","author":"shalev-shwartz","year":"2017","journal-title":"arXiv preprint arXiv 1708 06374"},{"key":"ref6","article-title":"Parameter sharing reinforcement learning architecture for multi agent driving behaviors","author":"kaushik","year":"2018","journal-title":"arXiv preprint arXiv 1811 07214"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref8","first-page":"583","article-title":"Learning driving behaviors for automated cars in unstructured environments","author":"kaushik","year":"2018","journal-title":"European Conference on Computer Vision"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500718"},{"key":"ref2","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"shalev-shwartz","year":"2016","journal-title":"arXiv preprint arXiv 1610 09756"},{"key":"ref1","article-title":"Concrete problems in ai safety","author":"amodei","year":"2016","journal-title":"arXiv preprint arXiv 1606 06565"},{"key":"ref9","article-title":"Memory-based control with recurrent neural networks","author":"heess","year":"2015","journal-title":"arXiv preprint arXiv 1512 04455"}],"event":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2019,12,6]]},"location":"Dali, China","end":{"date-parts":[[2019,12,8]]}},"container-title":["2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8953068\/8961374\/08961480.pdf?arnumber=8961480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:23:26Z","timestamp":1755800606000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8961480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/robio49542.2019.8961480","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}