{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:15:53Z","timestamp":1774455353849,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T00:00:00Z","timestamp":1649808000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T00:00:00Z","timestamp":1649808000000},"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"}]},{"DOI":"10.13039\/100017030","name":"Worcester Polytechnic Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017030","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,4,13]]},"DOI":"10.1109\/ismr48347.2022.9807609","type":"proceedings-article","created":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T20:09:49Z","timestamp":1656446989000},"page":"1-8","source":"Crossref","is-referenced-by-count":15,"title":["AMBF-RL: A real-time simulation based Reinforcement Learning toolkit for Medical Robotics"],"prefix":"10.1109","author":[{"given":"Vignesh Manoj","family":"Varier","sequence":"first","affiliation":[{"name":"Worcester Polytechnic Institute, WPI, 100 Institute Road,Robotics Engineering Department,MA,USA,01609"}]},{"given":"Dhruv Kool","family":"Rajamani","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute, WPI, 100 Institute Road,Robotics Engineering Department,MA,USA,01609"}]},{"given":"Farid","family":"Tavakkolmoghaddam","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute, WPI, 100 Institute Road,Robotics Engineering Department,MA,USA,01609"}]},{"given":"Adnan","family":"Munawar","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Laboratory for Computational Sensing and Robotics,Baltimore,Maryland,USA,21218"}]},{"given":"Gregory S","family":"Fischer","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute, WPI, 100 Institute Road,Robotics Engineering Department,MA,USA,01609"}]}],"member":"263","reference":[{"key":"ref39","article-title":"The problem with ddpg: understanding failures in deterministic environments with sparse rewards","volume":"abs 1911 11679","author":"matheron","year":"2019","journal-title":"CoRR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2017.69"},{"key":"ref33","first-page":"496","article-title":"The chai libraries","author":"conti","year":"2003","journal-title":"Proceedings of Eurohaptics 2003"},{"key":"ref32","author":"coumans","year":"2017","journal-title":"pybullet a python module for physics simulation in robotics games and machine learning"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635867"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989275"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.54294\/2dcog6"},{"key":"ref36","author":"hill","year":"2018","journal-title":"Stable Baselines"},{"key":"ref35","article-title":"Generative Adversarial Imitation Learning","volume":"29","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"Ros: an open-source robot operating system","volume":"3","author":"quigley","year":"2009","journal-title":"ICRA Workshop on Open Source Software"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.surg.2012.07.028"},{"key":"ref40","first-page":"1039","article-title":"GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms","author":"colas","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968568"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197573"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907809"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2012.2228858"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8205979"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN47096.2020.9223543"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","volume":"abs 1509 2971","author":"lillicrap","year":"2016","journal-title":"CoRR"},{"key":"ref19","article-title":"Hindsight Experience Replay","volume":"30","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2018.8441801"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891311"},{"key":"ref3","author":"dhariwal","year":"2017","journal-title":"OpenAI Baselines"},{"key":"ref6","article-title":"Robot Autonomy for Surgery","author":"yip","year":"2017","journal-title":"arXiv 1707 03080 [cs]"},{"key":"ref29","article-title":"Coppeliasim (formerly v-rep): a versatile and scalable robot simulation framework","author":"rohmer","year":"2013","journal-title":"Proc of the International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196730"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968109"},{"key":"ref7","first-page":"15","article-title":"Surgical Robotics Beyond Enhanced Dexterity Instrumentation","author":"kassahun","year":"0","journal-title":"International Journal of Computer Assisted Radiology and Surgery"},{"key":"ref2","article-title":"OpenAI Gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref9","first-page":"94150b","article-title":"Image-based tracking of the suturing needle during laparoscopic interventions","author":"speidel","year":"2015"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref20","article-title":"gym-gazebo2, a toolkit for reinforcement learning using ROS 2 and gazebo","volume":"abs 1903 6278","author":"lopez","year":"2019","journal-title":"CoRR"},{"key":"ref22","article-title":"Deepracer: Educational autonomous racing platform for experimentation with sim2real reinforcement learning","author":"balaji","year":"2019","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref42","article-title":"Noisy Networks for Exploration","author":"fortunato","year":"2019","journal-title":"CoRR"},{"key":"ref24","article-title":"Safe exploration in continuous action spaces","author":"dalal","year":"2018","journal-title":"CoRR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5220\/0007364701340144"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref44","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref26","article-title":"Open-Sourced Reinforcement Learning Environments for Surgical Robotics","author":"richter","year":"2020","journal-title":"CoRR"},{"key":"ref43","article-title":"Parameter Space Noise for Exploration","author":"plappert","year":"2018","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT.2019.8755235"}],"event":{"name":"2022 International Symposium on Medical Robotics (ISMR)","location":"GA, USA","start":{"date-parts":[[2022,4,13]]},"end":{"date-parts":[[2022,4,15]]}},"container-title":["2022 International Symposium on Medical Robotics (ISMR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9807425\/9807460\/09807609.pdf?arnumber=9807609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T20:16:12Z","timestamp":1658780172000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9807609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,13]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/ismr48347.2022.9807609","relation":{},"subject":[],"published":{"date-parts":[[2022,4,13]]}}}