{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T13:46:06Z","timestamp":1762609566224,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,12]],"date-time":"2023-11-12T00:00:00Z","timestamp":1699747200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3624062.3624170","type":"proceedings-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T13:53:39Z","timestamp":1699624419000},"page":"932-940","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Addressing Stale Gradients in Scalable Federated Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8588-2631","authenticated-orcid":false,"given":"Justin","family":"Stanley","sequence":"first","affiliation":[{"name":"Iowa State University, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8672-5317","authenticated-orcid":false,"given":"Ali","family":"Jannesari","sequence":"additional","affiliation":[{"name":"Iowa State University, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,11,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","unstructured":"M.\u00a0G. Bellemare Y. Naddaf J. Veness and M. Bowling. 2013. The Arcade Learning Environment: An Evaluation Platform for General Agents. Journal of Artificial Intelligence Research 47 (jun 2013) 253\u2013279. https:\/\/doi.org\/10.1613\/jair.3912","DOI":"10.1613\/jair.3912"},{"key":"e_1_3_2_2_2_1","unstructured":"Yuqing Du Olivia Watkins Zihan Wang C\u00e9dric Colas Trevor Darrell Pieter Abbeel Abhishek Gupta and Jacob Andreas. 2023. Guiding Pretraining in Reinforcement Learning with Large Language Models. arxiv:2302.06692\u00a0[cs.LG]"},{"key":"e_1_3_2_2_3_1","volume-title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures. arxiv:1802.01561\u00a0[cs.LG]","author":"Espeholt Lasse","year":"2018","unstructured":"Lasse Espeholt, Hubert Soyer, Remi Munos, Karen Simonyan, Volodymir Mnih, Tom Ward, Yotam Doron, Vlad Firoiu, Tim Harley, Iain Dunning, Shane Legg, and Koray Kavukcuoglu. 2018. IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures. arxiv:1802.01561\u00a0[cs.LG]"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2021.3125282"},{"key":"e_1_3_2_2_5_1","unstructured":"David Griffis. 2023. GitHub - dgriff777\/rl_a3c_pytorch: A3C LSTM Atari with Pytorch plus A3G design \u2014 github.com. https:\/\/github.com\/dgriff777\/rl_a3c_pytorch. [Accessed 29-Apr-2023]."},{"key":"e_1_3_2_2_6_1","unstructured":"Tian Li Anit\u00a0Kumar Sahu Manzil Zaheer Maziar Sanjabi Ameet Talwalkar and Virginia Smith. 2020. Federated Optimization in Heterogeneous Networks. arxiv:1812.06127\u00a0[cs.LG]"},{"key":"e_1_3_2_2_7_1","unstructured":"H.\u00a0Brendan McMahan Eider Moore Daniel Ramage Seth Hampson and Blaise\u00a0Ag\u00fcera y Arcas. 2023. Communication-Efficient Learning of Deep Networks from Decentralized Data. arxiv:1602.05629\u00a0[cs.LG]"},{"key":"e_1_3_2_2_8_1","unstructured":"Volodymyr Mnih Adri\u00e0\u00a0Puigdom\u00e8nech Badia Mehdi Mirza Alex Graves Timothy\u00a0P. Lillicrap Tim Harley David Silver and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. arxiv:1602.01783\u00a0[cs.LG]"},{"key":"e_1_3_2_2_9_1","unstructured":"Arun Nair Praveen Srinivasan Sam Blackwell Cagdas Alcicek Rory Fearon Alessandro\u00a0De Maria Vedavyas Panneershelvam Mustafa Suleyman Charles Beattie Stig Petersen Shane Legg Volodymyr Mnih Koray Kavukcuoglu and David Silver. 2015. Massively Parallel Methods for Deep Reinforcement Learning. arxiv:1507.04296\u00a0[cs.LG]"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"key":"e_1_3_2_2_11_1","unstructured":"John Schulman Sergey Levine Philipp Moritz Michael\u00a0I. Jordan and Pieter Abbeel. 2017. Trust Region Policy Optimization. arxiv:1502.05477\u00a0[cs.LG]"},{"key":"e_1_3_2_2_12_1","unstructured":"Han Shen Kaiqing Zhang Mingyi Hong and Tianyi Chen. 2022. Towards Understanding Asynchronous Advantage Actor-critic: Convergence and Linear Speedup. arxiv:2012.15511\u00a0[cs.LG]"},{"key":"e_1_3_2_2_13_1","unstructured":"David Silver Thomas Hubert Julian Schrittwieser Ioannis Antonoglou Matthew Lai Arthur Guez Marc Lanctot Laurent Sifre Dharshan Kumaran Thore Graepel Timothy Lillicrap Karen Simonyan and Demis Hassabis. 2017. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm. arxiv:1712.01815\u00a0[cs.AI]"},{"key":"e_1_3_2_2_14_1","unstructured":"Jianyu Wang Qinghua Liu Hao Liang Gauri Joshi and H.\u00a0Vincent Poor. 2020. Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization. arxiv:2007.07481\u00a0[cs.LG]"},{"key":"e_1_3_2_2_15_1","volume-title":"SPATL: Salient Parameter Aggregation and Transfer Learning for Heterogeneous Clients in Federated Learning. arxiv:2111.14345\u00a0[cs.LG]","author":"Yu Sixing","year":"2022","unstructured":"Sixing Yu, Phuong Nguyen, Waqwoya Abebe, Wei Qian, Ali Anwar, and Ali Jannesari. 2022. SPATL: Salient Parameter Aggregation and Transfer Learning for Heterogeneous Clients in Federated Learning. arxiv:2111.14345\u00a0[cs.LG]"},{"key":"e_1_3_2_2_16_1","unstructured":"Zheng Yu Yikuan Li Joseph Kim Kaixuan Huang Yuan Luo and Mengdi Wang. 2023. Deep Reinforcement Learning for Cost-Effective Medical Diagnosis. arxiv:2302.10261\u00a0[cs.LG]"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"S.\u00a0Kevin Zhou Hoang\u00a0Ngan Le Khoa Luu Hien\u00a0V. Nguyen and Nicholas Ayache. 2021. Deep reinforcement learning in medical imaging: A literature review. arxiv:2103.05115\u00a0[eess.IV]","DOI":"10.1016\/j.media.2021.102193"}],"event":{"name":"SC-W 2023: Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis","acronym":"SC-W 2023","location":"Denver CO USA"},"container-title":["Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624170","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624062.3624170","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T03:01:51Z","timestamp":1755745311000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624170"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,12]]},"references-count":17,"alternative-id":["10.1145\/3624062.3624170","10.1145\/3624062"],"URL":"https:\/\/doi.org\/10.1145\/3624062.3624170","relation":{},"subject":[],"published":{"date-parts":[[2023,11,12]]},"assertion":[{"value":"2023-11-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}