{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T12:44:23Z","timestamp":1730292263495,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T00:00:00Z","timestamp":1689552000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T00:00:00Z","timestamp":1689552000000},"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":[[2023,7,17]]},"DOI":"10.1109\/rcar58764.2023.10250060","type":"proceedings-article","created":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T17:36:59Z","timestamp":1695231419000},"page":"847-852","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning with Goal Relabeling and Dynamic Model for Robotic Tasks"],"prefix":"10.1109","author":[{"given":"Kun","family":"Dong","sequence":"first","affiliation":[{"name":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongle","family":"Luo","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Fang","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erkang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Song","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"10 537","article-title":"Trust the model when it is confident: Masked model-based actor-critic","volume":"33","author":"pan","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"5618","article-title":"Bidirectional model-based policy optimization","author":"lai","year":"2020","journal-title":"International Conference on Machine Learning"},{"article-title":"Imaginary hindsight experience replay: Curious model-based learning for sparse reward tasks","year":"2021","author":"mccarthy","key":"ref15"},{"key":"ref14","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"When to trust your model: Model-based policy optimization","volume":"32","author":"janner","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3057424"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3166555"},{"article-title":"Relay hindsight experience replay: Continual reinforcement learning for robot manipulation tasks with sparse rewards","year":"2022","author":"luo","key":"ref17"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197421"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"article-title":"Mher: Model-based hindsight experience replay","year":"2021","author":"yang","key":"ref18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"article-title":"Algorithmic framework for model-based deep reinforcement learning with theoretical guarantees","year":"2018","author":"luo","key":"ref23"},{"key":"ref26","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"article-title":"Benchmarking model-based reinforcement learning","year":"2019","author":"wang","key":"ref25"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"article-title":"World models","year":"2018","author":"ha","key":"ref22"},{"article-title":"Exploring model-based planning with policy networks","year":"2019","author":"wang","key":"ref21"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref8","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","volume":"31","author":"buckman","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref9","article-title":"Model-based value expansion for efficient model-free reinforcement learning","author":"feinberg","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning (ICML 2018)"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref4"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"article-title":"Updet: Universal multi-agent reinforcement learning via policy decoupling with transformers","year":"2021","author":"hu","key":"ref5"}],"event":{"name":"2023 IEEE International Conference on Real-time Computing and Robotics (RCAR)","start":{"date-parts":[[2023,7,17]]},"location":"Datong, China","end":{"date-parts":[[2023,7,20]]}},"container-title":["2023 IEEE International Conference on Real-time Computing and Robotics (RCAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10249208\/10249018\/10250060.pdf?arnumber=10250060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T18:07:13Z","timestamp":1696874833000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10250060\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,17]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/rcar58764.2023.10250060","relation":{},"subject":[],"published":{"date-parts":[[2023,7,17]]}}}