{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:48:22Z","timestamp":1730270902695,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981869","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"9040-9047","source":"Crossref","is-referenced-by-count":0,"title":["Backward Imitation and Forward Reinforcement Learning via Bi-directional Model Rollouts"],"prefix":"10.1109","author":[{"given":"Yuxin","family":"Pan","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology,Division of Emerging Interdisciplinary Areas under IPO,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangzhen","family":"Lin","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman","year":"2015"},{"key":"ref3","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1561\/9781601987037"},{"key":"ref5","article-title":"Recall traces: Backtracking models for efficient reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Goyal","year":"2019"},{"key":"ref6","first-page":"5618","article-title":"Bidirectional model-based policy optimization","volume-title":"International Conference on Machine Learning","author":"Lai"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref8","article-title":"Prediction and control with temporal segment models","volume-title":"International Conference on Machine Learning","author":"Mishra","year":"2017"},{"volume-title":"Understanding the asymptotic performance of model-based rl methods","year":"2018","author":"Whitney","key":"ref9"},{"key":"ref10","article-title":"Model imitation for model-based reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Wu","year":"2020"},{"volume-title":"Improving model-based rl with adaptive rollout using uncertainty estimation","year":"2018","author":"Nguyen","key":"ref11"},{"key":"ref12","article-title":"Learning to combat compounding-error in model-based reinforcement learning","volume-title":"NeurIPS 2019 Deep Reinforcement Learning Workshop","author":"Xiao","year":"2019"},{"key":"ref13","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","author":"Janner","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","article-title":"Forward-backward reinforcement learning","author":"Edwards","year":"2018","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_36"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196609"},{"key":"ref17","first-page":"1515","article-title":"Automatic goal generation for reinforcement learning agents","volume-title":"International conference on machine learning","author":"Florensa"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref19","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"Chua","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref21","article-title":"Benchmarking model-based reinforcement learning","author":"Langlois","year":"2019","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv preprint"},{"volume-title":"Model predictive control","year":"2013","author":"Camacho","key":"ref23"},{"key":"ref24","article-title":"Model-augmented actor-critic: Back-propagating through paths","volume-title":"International Conference on Learning Representations","author":"Clavera","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561298"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981869.pdf?arnumber=9981869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:26:04Z","timestamp":1706761564000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981869\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981869","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}