{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T18:21:11Z","timestamp":1773858071711,"version":"3.50.1"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42125503,42075137"],"award-info":[{"award-number":["42125503,42075137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342479","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"1207-1214","source":"Crossref","is-referenced-by-count":3,"title":["RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control"],"prefix":"10.1109","author":[{"given":"Yanfei","family":"Xiang","sequence":"first","affiliation":[{"name":"Ministry of Education, Key Laboratory for Earth System Modeling, Institute for Global Change Studies, Tsinghua University,Department of Earth System Science,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"University at Albany, State University of New York,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shu","family":"Hu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaomeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Ministry of Education, Key Laboratory for Earth System Modeling, Institute for Global Change Studies, Tsinghua University,Department of Earth System Science,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Wu","sequence":"additional","affiliation":[{"name":"Chengdu University of Information Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siwei","family":"Lyu","sequence":"additional","affiliation":[{"name":"University at Buffalo, State University of New York,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","article-title":"Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning","volume":"27","author":"Guo","year":"2014","journal-title":"NIPS"},{"key":"ref3","article-title":"Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images","volume":"28","author":"Watter","year":"2015","journal-title":"NIPS"},{"key":"ref4","author":"Yarats","year":"2021","journal-title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref6","first-page":"1329","article-title":"Benchmarking Deep Reinforcement Learning for Continuous Control","author":"Duan","year":"2016","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2019.00120"},{"key":"ref8","article-title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"NIPS"},{"key":"ref9","article-title":"Optimizing Expectations: From Deep Reinforcement Learning to Stochastic Computation Graphs","author":"Schulman","year":"2016","journal-title":"UC Berkeley"},{"key":"ref10","article-title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","author":"Schulman","year":"2018","journal-title":"arXiv"},{"key":"ref11","first-page":"1889","article-title":"Trust Region Policy Optimization","author":"Schulman","year":"2015","journal-title":"ICML"},{"key":"ref12","article-title":"Proximal Policy Optimization Algorithms","author":"Schulman","year":"2017","journal-title":"arXiv"},{"key":"ref13","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2019","journal-title":"arXiv"},{"key":"ref14","first-page":"387","article-title":"Deterministic Policy Gradient Algorithms","author":"Silver","year":"2014","journal-title":"ICML"},{"key":"ref15","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","author":"Fujimoto","year":"2018","journal-title":"arXiv"},{"key":"ref16","author":"Haarnoja","year":"2018","journal-title":"Soft Actor-Critic: Off-Policy Maximum En-tropy Deep Reinforcement Learning with a Stochastic Actor"},{"key":"ref17","author":"Haarnoja","year":"2017","journal-title":"Reinforcement Learning with Deep Energy-Based Policies"},{"key":"ref18","article-title":"Distributed Distributional Deterministic Policy Gradients","author":"Barth-Maron","year":"2018","journal-title":"arXiv"},{"key":"ref19","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"Ziebart","year":"2008","journal-title":"Aaai"},{"key":"ref20","first-page":"1928","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"Mnih","year":"2016","journal-title":"ICML"},{"key":"ref21","article-title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","author":"Srinivas","year":"2020","journal-title":"arXiv"},{"key":"ref22","article-title":"Automatic Data Augmentation for Generalization in Deep Reinforcement Learning","author":"Raileanu","year":"2021","journal-title":"arXiv"},{"key":"ref23","first-page":"11920","article-title":"Reinforcement Learning with Prototypical Represen-tations","author":"Yarats","year":"2021","journal-title":"ICML"},{"key":"ref24","first-page":"6","article-title":"On the Model-Based Stochastic Value Gradient for Continuous Reinforcement Learning","author":"Amos","year":"2021","journal-title":"L4DC"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2018.8461039"},{"key":"ref26","article-title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","author":"Zhu","year":"2020","journal-title":"arXiv"},{"key":"ref27","first-page":"1300","article-title":"ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots","author":"Ahn","year":"2020","journal-title":"CoRL"},{"key":"ref28","article-title":"Unsupervised State Representation Learning in Atari","volume":"32","author":"Anand","year":"2019","journal-title":"NIPS"},{"key":"ref29","article-title":"State of the Art Control of Atari Games Using Shallow Reinforcement Learning","author":"Liang","year":"2016","journal-title":"arXiv"},{"key":"ref30","volume-title":"RLLib: Lightweight standard and on\/off policy reinforcement learning library (C++)","author":"Abeyruwan","year":"2013"},{"key":"ref31","article-title":"Reinforcement learning benchmarks and bake-offs ii","volume":"17","author":"Dutech","year":"2005","journal-title":"NIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v35i3.2548"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273590"},{"key":"ref34","article-title":"Revisiting Design Choices in Proximal Policy Optimization","author":"Hsu","year":"2020","journal-title":"arXiv"},{"key":"ref35","volume-title":"RB2: Robotic Manipulation Benchmarking with a Twist","author":"Dasari","year":"2022"},{"key":"ref36","article-title":"Morel: Model-based offline reinforcement learning","author":"Kidambi","year":"2020","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-62579-5_22"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2012.6386109"},{"key":"ref39","volume-title":"DeepMind Control Suite","author":"Tassa","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2017.7989250"},{"key":"ref41","article-title":"Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning","author":"Gupta","year":"2017","journal-title":"arXiv"},{"key":"ref42","article-title":"Multi-Goal Reinforcement Learning: Chal-lenging Robotics Environments and Request for Research","author":"Plappert","year":"2018","journal-title":"arXiv"},{"key":"ref43","article-title":"Hardware Conditioned Policies for Multi-Robot Transfer Learning","author":"Chen","year":"2019","journal-title":"arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2018.8593894"},{"key":"ref45","article-title":"Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates","author":"Gu","year":"2016","journal-title":"arXiv"},{"key":"ref46","first-page":"465","article-title":"PILCO: a model-based and data-efficient approach to policy search","volume-title":"Proceedings of the 28th International Conference on International Conference on Machine Learning, Madison, WI, USA","author":"Deisenroth"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2015.7139807"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref51","article-title":"Mastering Atari with Discrete World Models","author":"Hafner","year":"2022","journal-title":"arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.7763\/IJMLC.2015.V5.489"},{"key":"ref53","first-page":"3061","article-title":"Revisiting Fundamentals of Experience Replay","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Fedus","year":"2022"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342479.pdf?arnumber=10342479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:18:16Z","timestamp":1703031496000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342479\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342479","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}