{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:18:19Z","timestamp":1730229499783,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/icarcv.2018.8581310","type":"proceedings-article","created":{"date-parts":[[2019,1,9]],"date-time":"2019-01-09T18:57:00Z","timestamp":1547060220000},"page":"286-291","source":"Crossref","is-referenced-by-count":2,"title":["Learning to Run with Potential-Based Reward Shaping and Demonstrations from Video Data"],"prefix":"10.1109","author":[{"given":"Aleksandra","family":"Malysheva","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Kudenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aleksei","family":"Shpilman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"463","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","volume":"98","author":"randl\u00f8v","year":"1998","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1190"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref12"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref13"},{"key":"ref14","first-page":"429","article-title":"Learning from demonstration for shaping through inverse reinforcement learning","author":"suay","year":"2016","journal-title":"Proceedings of the 2016 International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref15","first-page":"3352","article-title":"Reinforcement learning from demonstration through shaping","author":"brys","year":"2015","journal-title":"IJCAI"},{"journal-title":"Deepmimic Example-guided deep reinforcement learning of physics-based character skills","year":"2018","author":"peng","key":"ref16"},{"journal-title":"Imitation from observation Learning to imitate behaviors from raw video via context translation","year":"2017","author":"liu","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"journal-title":"Dense-pose Dense human pose estimation in the wild","year":"2018","author":"g\u00fcler","key":"ref19"},{"key":"ref4","article-title":"Reinforcement Learning to Run… Fast","author":"ja?kowski","year":"2018","journal-title":"NIPS 2017 Competition Book"},{"key":"ref3","article-title":"Learning to run challenge: Synthesizing physiologically accurate motion using deep reinforcement learning","author":"kidzi?ski","year":"2018","journal-title":"NIPS 2017 Competition Book Springer"},{"key":"ref6","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"ICML"},{"key":"ref5","article-title":"Learning to run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments","author":"kidzi?ski","year":"2018","journal-title":"NIPS 2017 Competition Book"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"puterman","key":"ref8"},{"key":"ref7","first-page":"aai8410337","author":"sutton","year":"1984","journal-title":"Temporal credit assignment in reinforcement learning"},{"journal-title":"NASA gives MIT a humanoid robot to develop software for future space missions","year":"2015","author":"conner-simons","key":"ref2"},{"key":"ref1","article-title":"Development of a loca prosthetic limb using artificial intelligence","volume":"4","author":"alshamsi","year":"2016","journal-title":"International Journal of Innovative Research in Computer and Communication Engineering"},{"key":"ref9","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"}],"event":{"name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","start":{"date-parts":[[2018,11,18]]},"location":"Singapore","end":{"date-parts":[[2018,11,21]]}},"container-title":["2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8564369\/8580630\/08581310.pdf?arnumber=8581310","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:46:29Z","timestamp":1598233589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8581310\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icarcv.2018.8581310","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}