{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T09:16:50Z","timestamp":1730279810957,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T00:00:00Z","timestamp":1687132800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T00:00:00Z","timestamp":1687132800000},"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":[[2023,6,19]]},"DOI":"10.1109\/iwqos57198.2023.10188703","type":"proceedings-article","created":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T17:21:00Z","timestamp":1690478460000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["High-throughput Sampling, Communicating and Training for Reinforcement Learning Systems"],"prefix":"10.1109","author":[{"given":"Laiping","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Intelligence & Computing, Tianjin University,Tianjin Key Lab. of Advanced Networking,Tianjin,China"}]},{"given":"Xinan","family":"Dai","sequence":"additional","affiliation":[{"name":"College of Intelligence & Computing, Tianjin University,Tianjin Key Lab. of Advanced Networking,Tianjin,China"}]},{"given":"Zhixin","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Intelligence & Computing, Tianjin University,Tianjin Key Lab. of Advanced Networking,Tianjin,China"}]},{"given":"Yusong","family":"Xin","sequence":"additional","affiliation":[{"name":"College of Intelligence & Computing, Tianjin University,Tianjin Key Lab. of Advanced Networking,Tianjin,China"}]},{"given":"Yitao","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Intelligence & Computing, Tianjin University,Tianjin Key Lab. of Advanced Networking,Tianjin,China"}]},{"given":"Jun","family":"Qian","sequence":"additional","affiliation":[{"name":"Huawei,Noahs Ark Lab,Beijing,China"}]},{"given":"Jun","family":"Yao","sequence":"additional","affiliation":[{"name":"Huawei,Noahs Ark Lab,Beijing,China"}]},{"given":"Keqiu","family":"Li","sequence":"additional","affiliation":[{"name":"College of Intelligence & Computing, Tianjin University,Tianjin Key Lab. of Advanced Networking,Tianjin,China"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Ga3c: Gpu-based a3c for deep reinforcement learning","author":"babaeizadeh","year":"2016","journal-title":"CoRR abs\/1611 06256"},{"key":"ref12","article-title":"Actorq: Quantization for actor-learner distributed reinforcement learning","author":"lam","year":"0","journal-title":"ICLR Hardware Aware Efficient Training Workshop at ICLR 2021 Virtual"},{"key":"ref15","article-title":"Elegantrl-podracer: Scalable and elastic library for cloud-native deep reinforcement learning","author":"liu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref14","first-page":"7652","article-title":"Sample factory: Egocentric 3d control from pixels at 100000 fps with asynchronous reinforcement learning","author":"petrenko","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref31","article-title":"Cleanrl: High-quality single-file implementations of deep reinforcement learning algorithms","author":"huang","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478323"},{"key":"ref11","article-title":"Seed rl: Scalable and efficient deep-rl with accelerated central inference","author":"espeholt","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref10","article-title":"Acme: A research framework for distributed reinforcement learning","author":"hoffman","year":"0","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2851664"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref17","first-page":"980","article-title":"Low-precision reinforcement learning: Running soft actor-critic in half precision","volume":"139","author":"bj\u00f6rck","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78713-4_5"},{"key":"ref19","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"journal-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref18"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"1054","DOI":"10.1109\/TNN.1998.712192","article-title":"Reinforcement learning: An introduction","volume":"9","author":"sutton","year":"1998","journal-title":"IEEE Transactions on Neural Networks"},{"journal-title":"Huawei","article-title":"Mindspore","year":"2021","key":"ref23"},{"key":"ref26","first-page":"463","article-title":"A unified architecture for accelerating distributed dnn training in heterogeneous gpu\/cpu clusters","author":"jiang","year":"0","journal-title":"Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation"},{"key":"ref25","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":"ref20","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems","year":"2015","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3528535.3565249"},{"journal-title":"Kungfu A high-performance distributed training framework for deep learning","year":"2020","author":"dongdong chen","key":"ref28"},{"key":"ref27","article-title":"EnvPool: A highly parallel reinforcement learning environment execution engine","author":"weng","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref29","first-page":"561","article-title":"Ray: A distributed framework for emerging {AI} applications","author":"moritz","year":"0","journal-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)"},{"key":"ref8","first-page":"1407","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","author":"espeholt","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref7","first-page":"6411","article-title":"Simulation-based reinforcement learning for real-world autonomous driving","author":"osiski","year":"0","journal-title":"2020 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref9","first-page":"3053","article-title":"Rllib: Abstractions for distributed reinforcement learning","author":"liang","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2022.101754"},{"key":"ref6","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in starcraft ii using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"}],"event":{"name":"2023 IEEE\/ACM 31st International Symposium on Quality of Service (IWQoS)","start":{"date-parts":[[2023,6,19]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2023,6,21]]}},"container-title":["2023 IEEE\/ACM 31st International Symposium on Quality of Service (IWQoS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10188660\/10188690\/10188703.pdf?arnumber=10188703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T17:38:44Z","timestamp":1692034724000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10188703\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,19]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iwqos57198.2023.10188703","relation":{},"subject":[],"published":{"date-parts":[[2023,6,19]]}}}