{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:19:12Z","timestamp":1730229552151,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,13]],"date-time":"2020-12-13T00:00:00Z","timestamp":1607817600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,13]],"date-time":"2020-12-13T00:00:00Z","timestamp":1607817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,13]],"date-time":"2020-12-13T00:00:00Z","timestamp":1607817600000},"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":[[2020,12,13]]},"DOI":"10.1109\/icarcv50220.2020.9305338","type":"proceedings-article","created":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T10:23:59Z","timestamp":1610274239000},"page":"1104-1111","source":"Crossref","is-referenced-by-count":1,"title":["Autonomous Curriculum Generation for Self-Learning Agents"],"prefix":"10.1109","author":[{"given":"Anil","family":"Kurkcu","sequence":"first","affiliation":[]},{"given":"Domenico","family":"Campolo","sequence":"additional","affiliation":[]},{"given":"Keng Peng","family":"Tee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection","year":"2016","author":"levine","key":"ref10"},{"journal-title":"Emergence of locomotion behaviours in rich environments","year":"2017","author":"heess","key":"ref11"},{"journal-title":"Pretraining with Non-expert Human Demonstration for Deep Reinforcement Learning","year":"2018","author":"de la cruz","key":"ref12"},{"journal-title":"Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuo-motor Policies","year":"2018","author":"sax","key":"ref13"},{"journal-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","year":"2017","author":"gupta","key":"ref14"},{"journal-title":"CLIC Curriculum Learning and Imitation for object Control in nonrewarding environments","year":"2019","author":"fournier","key":"ref15"},{"journal-title":"Learning Curriculum Policies for Reinforcement Learning","year":"2018","author":"narvekar","key":"ref16"},{"key":"ref17","article-title":"Source Task Creation for Curriculum Learning","author":"narvekar","year":"2016","journal-title":"Proceedings of the 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016)"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"journal-title":"Stable Baselines","year":"2018","author":"hill","key":"ref28"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"journal-title":"OpenAI Baselines","year":"2017","author":"dhariwal","key":"ref27"},{"journal-title":"A Deep Reinforcement-Learning-based Driving Policy for Autonomous Road Vehicles","year":"2019","author":"makantasis","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref29","first-page":"6439","author":"tee","year":"2018","journal-title":"Towards Emergence of Tool Use in Robots Automatic Tool Recognition and Use Without Prior Tool Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917735594"},{"journal-title":"A survey on policy search algorithms for learning robot controllers in a handful of trials","year":"2018","author":"chatzilygeroudis","key":"ref8"},{"key":"ref7","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"journal-title":"QT-Opt Scalable deep reinforcement learning for vision-based robotic manipulation","year":"2018","author":"kalashnikov","key":"ref9"},{"key":"ref1","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16111-7_23"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/353"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"journal-title":"Benchmarking deep reinforcement learning for continuous control","year":"2016","author":"duan","key":"ref24"},{"journal-title":"Agent Embeddings A Latent Representation for Pole-Balancing Networks","year":"2018","author":"chang","key":"ref23"},{"journal-title":"Ope-nAI Gym","year":"2016","author":"brockman","key":"ref26"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref25"}],"event":{"name":"2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV)","start":{"date-parts":[[2020,12,13]]},"location":"Shenzhen, China","end":{"date-parts":[[2020,12,15]]}},"container-title":["2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9305021\/9305302\/09305338.pdf?arnumber=9305338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:08:30Z","timestamp":1656374910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9305338\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,13]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icarcv50220.2020.9305338","relation":{},"subject":[],"published":{"date-parts":[[2020,12,13]]}}}