{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T13:38:37Z","timestamp":1768916317680,"version":"3.49.0"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561119","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"4116-4122","source":"Crossref","is-referenced-by-count":3,"title":["Learning from Demonstration without Demonstrations"],"prefix":"10.1109","author":[{"given":"Tom","family":"Blau","sequence":"first","affiliation":[]},{"given":"Philippe","family":"Morere","sequence":"additional","affiliation":[]},{"given":"Gilad","family":"Francis","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Go-explore: a new approach for hard-exploration problems","author":"ecoffet","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2931199"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461096"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/027836402320556421"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/02783640122067453"},{"key":"ref37","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2888947"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.026"},{"key":"ref34","article-title":"Learning to plan via neural exploration-exploitation trees","author":"chen","year":"2019"},{"key":"ref10","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"NIPS Deep Learning Symposium"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(97)00043-2"},{"key":"ref12","article-title":"Reinforcement learning from demonstration through shaping","author":"brys","year":"2015","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11757","article-title":"Deep q-learning from demonstrations","author":"hester","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref15","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref16","article-title":"How can we define intrinsic motivation?","author":"oudeyer","year":"2008","journal-title":"International Conference on Epigenetic Robotics Modeling Cognitive Development in Robotic Systems"},{"key":"ref17","article-title":"Exploration in model-based reinforcement learning by empirically estimating learning progress","author":"lopes","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390288"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.619371"},{"key":"ref4","article-title":"Learning from demonstration","author":"schaal","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/70.508439"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref6","article-title":"Rapidly-exploring random trees: A new tool for path planning","author":"lavalle","year":"1998","journal-title":"Department of Computer Science Iowa State University Tech Rep"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844730"},{"key":"ref5","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1994.350934"},{"key":"ref20","article-title":"DORA the explorer: Directed outreaching reinforcement action-selection","author":"fox","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF02458840"},{"key":"ref48","article-title":"Random features for large-scale kernel machines","author":"rahimi","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Bayesian RL for goal-only rewards","author":"morere","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2003.1248805"},{"key":"ref21","article-title":"Deep exploration via bootstrapped DQN","author":"osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref42","article-title":"OpenAI Gym","author":"brockman","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref41","article-title":"Garage: A toolkit for reproducible reinforcement learning research","year":"2019"},{"key":"ref23","article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","author":"stadie","year":"2015"},{"key":"ref44","article-title":"Vime: Variational information maximizing exploration","author":"houthooft","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11830","article-title":"Bayesian functional optimization","author":"vien","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref43","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref25","article-title":"Using trajectory data to improve bayesian optimization for reinforcement learning","author":"wilson","year":"2014","journal-title":"The Journal of Machine Learning Research"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561119.pdf?arnumber=9561119","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:55:18Z","timestamp":1673564118000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561119\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561119","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}