{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:14:14Z","timestamp":1740100454329,"version":"3.37.3"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636369","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"2376-2382","source":"Crossref","is-referenced-by-count":2,"title":["CLAMGen: Closed-Loop Arm Motion Generation via Multi-view Vision-Based RL"],"prefix":"10.1109","author":[{"given":"Iretiayo","family":"Akinola","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zizhao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Allen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Soft actor-critic algorithms and applications","year":"2018","author":"haarnoja","key":"ref39"},{"key":"ref38","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"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"article-title":"Residual policy learning","year":"2018","author":"silver","key":"ref32"},{"article-title":"Improving sample efficiency in model-free reinforcement learning from images","year":"2019","author":"yarats","key":"ref31"},{"article-title":"Reinforcement learning with unsupervised auxiliary tasks","year":"2016","author":"jaderberg","key":"ref30"},{"article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","year":"2016","author":"coumans","key":"ref37"},{"key":"ref36","first-page":"1312","article-title":"Universal value function approximators","author":"schaul","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref35","first-page":"5831","article-title":"Addressing sample complexity in visual tasks using her and hallucinatory gans","author":"sahni","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1109\/TRO.2020.2988642","article-title":"Tossing-bot: Learning to throw arbitrary objects with residual physics","author":"zeng","year":"2020","journal-title":"IEEE Transactions on Robotics"},{"article-title":"Universal planning networks","year":"2018","author":"srinivas","key":"ref10"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"article-title":"Motion planning networks","year":"2018","author":"qureshi","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460730"},{"article-title":"Robot motion planning in learned latent spaces","year":"2018","author":"ichter","key":"ref13"},{"article-title":"Data-driven planning via imitation learning","year":"2017","author":"choudhury","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593947"},{"article-title":"Unsupervised path regression networks","year":"2020","author":"p\u00e1ndy","key":"ref16"},{"article-title":"Hierarchical imitation and reinforcement learning","year":"2018","author":"le","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.01.054"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.026"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152817"},{"article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","year":"2018","author":"kalashnikov","key":"ref27"},{"article-title":"Probabilistic roadmaps for robot path planning","year":"1998","author":"kavraki","key":"ref3"},{"article-title":"Asymptotically optimal sampling-based planners","year":"2019","author":"bekris","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197181"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980280"},{"key":"ref8","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-8997-2_29"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref9","first-page":"2154","article-title":"Value iteration networks","author":"tamar","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Rapidly-exploring random trees: A new tool for path planning","year":"1998","author":"lavalle","key":"ref1"},{"key":"ref20","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2019","journal-title":"International Conference on Machine Learning"},{"article-title":"Learning a decentralized multi-arm motion planner","year":"2020","author":"ha","key":"ref22"},{"article-title":"A critical investigation of deep reinforcement learning for navigation","year":"2018","author":"dhiman","key":"ref21"},{"article-title":"Curl: Contrastive unsupervised representations for reinforcement learning","year":"2020","author":"srinivas","key":"ref24"},{"article-title":"Stable baselines","year":"2018","author":"hill","key":"ref41"},{"article-title":"Learning latent dynamics for planning from pixels","year":"2018","author":"hafner","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461184"},{"article-title":"Learning vision-based reactive policies for obstacle avoidance","year":"2020","author":"aljalbout","key":"ref25"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2021,9,27]]},"location":"Prague, Czech Republic","end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636369.pdf?arnumber=9636369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T22:40:47Z","timestamp":1674081647000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636369\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636369","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}