{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T19:24:50Z","timestamp":1778181890959,"version":"3.51.4"},"reference-count":91,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197465","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"2746-2754","source":"Crossref","is-referenced-by-count":79,"title":["DeepRacer: Autonomous Racing Platform for Experimentation with Sim2Real Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Bharathan","family":"Balaji","sequence":"first","affiliation":[]},{"given":"Sunil","family":"Mallya","sequence":"additional","affiliation":[]},{"given":"Sahika","family":"Genc","sequence":"additional","affiliation":[]},{"given":"Saurabh","family":"Gupta","sequence":"additional","affiliation":[]},{"given":"Leo","family":"Dirac","sequence":"additional","affiliation":[]},{"given":"Vineet","family":"Khare","sequence":"additional","affiliation":[]},{"given":"Gourav","family":"Roy","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Yunzhe","family":"Tao","sequence":"additional","affiliation":[]},{"given":"Brian","family":"Townsend","sequence":"additional","affiliation":[]},{"given":"Eddie","family":"Calleja","sequence":"additional","affiliation":[]},{"given":"Sunil","family":"Muralidhara","sequence":"additional","affiliation":[]},{"given":"Dhanasekar","family":"Karuppasamy","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.033"},{"key":"ref72","article-title":"Poppy project: open-source fabrication of 3d printed humanoid robot for science, education and art","author":"lapeyre","year":"2014"},{"key":"ref71","article-title":"Mushr: A low-cost, open-source robotic racecar for education and research","author":"srinivasa","year":"2019"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ISECon.2017.7910242"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.056"},{"key":"ref77","first-page":"1","article-title":"Driving policy transfer via modularity and abstraction","author":"mueller","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(92)90058-6"},{"key":"ref75","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1109\/37.257890","article-title":"Acquiring robot skills via reinforcement learning","volume":"14","author":"gullapalli","year":"1994","journal-title":"IEEE Control Systems Magazine"},{"key":"ref78","article-title":"Deep drone racing: From simulation to reality with domain randomization","author":"loquercio","year":"2019"},{"key":"ref79","article-title":"Self-driving scale car trained by deep reinforcement learning","author":"zhang","year":"2019"},{"key":"ref33","article-title":"On the sample complexity of reinforcement learning","author":"kakade","year":"2003","journal-title":"Ph D Dissertation"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00493"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/BF00117447"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-6451-2_4"},{"key":"ref35","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume":"97","author":"cobbe","year":"0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59496-5_337"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967363"},{"key":"ref61","first-page":"734","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","volume":"87","author":"matas","year":"0"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2018.2876958"},{"key":"ref28","author":"hightower","year":"2017","journal-title":"Kubernetes Up and Running Dive Into the Future of Infrastructure"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1201\/9781315265285-22"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794310"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794236"},{"key":"ref66","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume":"78","author":"dosovitskiy","year":"0"},{"key":"ref29","article-title":"Reinforcement Learning Coach","author":"caspi","year":"2017"},{"key":"ref67","article-title":"Donkey car: An opensource DIY self driving platform for small scale cars","author":"roscoe","year":"2019"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989179"},{"key":"ref69","article-title":"F1\/10: An open-source autonomous cyber-physical platform","author":"o\u2019kelly","year":"2019"},{"key":"ref2","article-title":"Learning dexterous in-hand manipulation","author":"andrychowicz","year":"2018"},{"key":"ref1","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","volume":"80","author":"espeholt","year":"0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref21","first-page":"3053","article-title":"RLlib: Abstractions for distributed reinforcement learning","volume":"80","author":"liang","year":"0"},{"key":"ref24","first-page":"700","article-title":"Domain randomization for simulation-based policy optimization with transferability assessment","author":"muratore","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref23","first-page":"1","article-title":"Sim-to-real transfer of robotic control with dynamics randomization","author":"peng","year":"2018","journal-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref26","first-page":"1480","article-title":"Darla: Improving zero-shot transfer in reinforcement learning","author":"higgins","year":"0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref51","first-page":"561","article-title":"Ray: A distributed framework for emerging {AI} applications","author":"moritz","year":"2018","journal-title":"13th USENIX Symposium on Operating Systems Design and Implementation ( OSDI 18)"},{"key":"ref91","first-page":"5","article-title":"Ros: an open-source robot operating system","volume":"3","author":"quigley","year":"2009","journal-title":"ICRA Workshop on Open Source Software"},{"key":"ref90","first-page":"2","article-title":"Docker: lightweight linux containers for consistent development and deployment","volume":"2014","author":"merkel","year":"2014","journal-title":"Linux Journal"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462971"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2347059"},{"key":"ref55","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"0"},{"key":"ref54","article-title":"Epopt: Learning robust neural network policies using model ensembles","author":"rajeswaran","year":"2016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354126"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460655"},{"key":"ref11","first-page":"799","article-title":"Autonomous helicopter flight via reinforcement learning","author":"kim","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref12","article-title":"CAD2RL: Real single-image flight without a single real image","author":"sadeghi","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794065"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref82","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2896449"},{"key":"ref17","article-title":"OpenAI Gym","author":"brockman","year":"2016"},{"key":"ref84","article-title":"Amazon SageMaker","year":"2019"},{"key":"ref18","first-page":"767","article-title":"Surreal: Open-source reinforcement learning framework and robot manipulation benchmark","author":"fan","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref83","article-title":"AWS RoboMaker","year":"2019"},{"key":"ref19","first-page":"270","article-title":"Gpu-accelerated robotic simulation for distributed reinforcement learning","volume":"87","author":"liang","year":"0"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3390\/s18113650"},{"key":"ref89","first-page":"87","article-title":"Jupyter notebooks-a publishing format for reproducible computational workflows","author":"kluyver","year":"2016","journal-title":"ELPUB"},{"key":"ref4","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","volume":"78","author":"rusu","year":"0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593722"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1126\/scirobotics.aau5872","article-title":"Learning agile and dynamic motor skills for legged robots","volume":"4","author":"hwangbo","year":"2019","journal-title":"Robotics Science"},{"key":"ref85","article-title":"Amazon S3","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793979"},{"key":"ref86","article-title":"Redis","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594352"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"ref87","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0"},{"key":"ref88","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"80","author":"haarnoja","year":"0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref46","article-title":"Setting up a benchmark environment for deep reinforcement learning","author":"oguz","year":"0"},{"key":"ref45","article-title":"Deepmind control suite","author":"tassa","year":"2018"},{"key":"ref48","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref47","article-title":"Openai baselines","author":"dhariwal","year":"2017","journal-title":"GitHub repository GitHub"},{"key":"ref42","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11694","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197465.pdf?arnumber=9197465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T13:59:46Z","timestamp":1668779986000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197465","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}