{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T21:07:42Z","timestamp":1776287262435,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T00:00:00Z","timestamp":1554336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and communications Technology Promotion","doi-asserted-by":"publisher","award":["1711073574"],"award-info":[{"award-number":["1711073574"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2017R1C1B5017414, NRF-2016M3C4A7952587, 21A20151113068"],"award-info":[{"award-number":["NRF-2017R1C1B5017414, NRF-2016M3C4A7952587, 21A20151113068"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,4,4]]},"DOI":"10.1145\/3297858.3304058","type":"proceedings-article","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T18:38:43Z","timestamp":1554403123000},"page":"499-513","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":55,"title":["FA3C"],"prefix":"10.1145","author":[{"given":"Hyungmin","family":"Cho","sequence":"first","affiliation":[{"name":"Hongik University, Seoul, Rebublic of Korea"}]},{"given":"Pyeongseok","family":"Oh","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Rebublic of Korea"}]},{"given":"Jiyoung","family":"Park","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Rebublic of Korea"}]},{"given":"Wookeun","family":"Jung","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Rebublic of Korea"}]},{"given":"Jaejin","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Rebublic of Korea"}]}],"member":"320","published-online":{"date-parts":[[2019,4,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"key":"e_1_3_2_1_2_1","volume-title":"Retrieved","year":"2018","unstructured":"Altera. 2018. Embedded Memory in Altera FPGAs. (2018). Retrieved Jan. 20, 2019 from https:\/\/www.intel.com\/content\/www\/us\/en\/programmable\/solutions\/technology\/memory\/embedded.html"},{"key":"e_1_3_2_1_3_1","volume-title":"Retrieved","author":"Services Amazon Web","year":"2019","unstructured":"Amazon Web Services, Inc. 2019. Amazon EC2 F1 Instances. (2019). Retrieved Jan. 20, 2019 from https:\/\/aws.amazon.com\/ec2\/instance-types\/f1\/"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021738"},{"key":"e_1_3_2_1_5_1","unstructured":"Mohammad Babaeizadeh Iuri Frosio Stephen Tyree Jason Clemons and Jan Kautz. 2017. Reinforcement Learning thorugh Asynchronous Advantage Actor-Critic on a GPU. In ICLR ."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/2832747.2832830"},{"key":"e_1_3_2_1_7_1","volume-title":"Humberto Nicol\u00e1 s Castej\u00f3 n Mart'i nez, and Arjun Chandra","author":"Clemente Alfredo V.","year":"2017","unstructured":"Alfredo V. Clemente, Humberto Nicol\u00e1 s Castej\u00f3 n Mart'i nez, and Arjun Chandra. 2017. Efficient Parallel Methods for Deep Reinforcement Learning. arXiv preprint (2017). arxiv: 1705.04862"},{"key":"e_1_3_2_1_8_1","volume-title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks. arXiv preprint","author":"Fernando Chrisantha","year":"2017","unstructured":"Chrisantha Fernando, Dylan Banarse, Charles Blundell, Yori Zwols, David Ha, Andrei A. Rusu, Alexander Pritzel, and Daan Wierstra. 2017. PathNet: Evolution Channels Gradient Descent in Super Neural Networks. arXiv preprint (2017). arxiv: 1701.08734"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.25"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"e_1_3_2_1_11_1","volume-title":"Retrieved","author":"Hinton Geoffrey","year":"2012","unstructured":"Geoffrey Hinton, Nitish Srivastava, and Kevin Swersky. 2012. Overview of mini-batch gradient descent. (2012). Retrieved Jan. 20, 2019 from http:\/\/www.cs.toronto.edu\/ tijmen\/csc321\/slides\/lecture_slides_lec6.pdf"},{"key":"e_1_3_2_1_12_1","volume-title":"Tom Schaul, Joel Z. Leibo, David Silver, and Koray Kavukcuoglu.","author":"Jaderberg Max","year":"2016","unstructured":"Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki, Tom Schaul, Joel Z. Leibo, David Silver, and Koray Kavukcuoglu. 2016. Reinforcement Learning with Unsupervised Auxiliary Tasks. arXiv preprint (2016). arxiv: 1611.05397"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446050"},{"key":"e_1_3_2_1_15_1","volume-title":"Asynchronous deep reinforcement learning. (2016). Retrieved","author":"Miyoshi Kosuke","year":"2018","unstructured":"Kosuke Miyoshi. 2016. Asynchronous deep reinforcement learning. (2016). Retrieved Aug. 7, 2018 from https:\/\/github.com\/miyosuda\/async_deep_reinforce"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045594"},{"key":"e_1_3_2_1_17_1","volume-title":"Playing Atari With Deep Reinforcement Learning. NIPS Deep Learning Workshop .","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller, Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing Atari With Deep Reinforcement Learning. NIPS Deep Learning Workshop ."},{"key":"e_1_3_2_1_18_1","volume-title":"Nature","volume":"518","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin A. Riedmiller, Andreas Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, and Demis Hassabis. 2015. Human-level control through deep reinforcement learning. Nature, Vol. 518, 7540 (2015), 529--533."},{"key":"e_1_3_2_1_19_1","volume-title":"Vedavyas Panneershelvam, Mustafa Suleyman, Charles Beattie, Stig Petersen, Shane Legg, Volodymyr Mnih, Koray Kavukcuoglu, and David Silver.","author":"Nair Arun","year":"2015","unstructured":"Arun Nair, Praveen Srinivasan, Sam Blackwell, Cagdas Alcicek, Rory Fearon, Alessandro De 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 preprint.arxiv: 1507.04296"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021740"},{"key":"e_1_3_2_1_21_1","volume-title":"Retrieved","author":"NVIDIA.","year":"2018","unstructured":"NVIDIA. 2018. cuBLAS Dense Linear Algebra on GPUs. (2018). Retrieved Jan. 20, 2019 from https:\/\/developer.nvidia.com\/cublas"},{"key":"e_1_3_2_1_22_1","volume-title":"Retrieved","author":"NVIDIA.","year":"2018","unstructured":"NVIDIA. 2018. NVIDIA cuDNN GPU Accelerated Deep Learning. (2018). Retrieved Jan. 20, 2019 from https:\/\/developer.nvidia.com\/cudnn"},{"key":"e_1_3_2_1_23_1","volume-title":"NIPS Workshop .","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in PyTorch. In NIPS Workshop ."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847265"},{"key":"e_1_3_2_1_25_1","volume-title":"Progressive Neural Networks. arXiv preprint","author":"Rusu Andrei A.","year":"2016","unstructured":"Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, and Raia Hadsell. 2016. Progressive Neural Networks. arXiv preprint (2016). arxiv: 1606.04671"},{"key":"e_1_3_2_1_26_1","unstructured":"Herman Schmit and Randy Huang. 2016. Dissecting Xeon"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934583.2953983"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195659"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_2_1_30_1","volume-title":"Koray Kavukcuoglu, and Nando de Freitas.","author":"Wang Ziyu","year":"2016","unstructured":"Ziyu Wang, Victor Bapst, Nicolas Heess, Volodymyr Mnih, R\u00e9 mi Munos, Koray Kavukcuoglu, and Nando de Freitas. 2016. Sample Efficient Actor-Critic with Experience Replay. arXiv preprint.arxiv: 1611.01224"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062207"},{"key":"e_1_3_2_1_32_1","volume-title":"Retrieved","year":"2017","unstructured":"Xilinx. 2017. Block Memory Generator,. (2017). Retrieved Jan. 20, 2019 from https:\/\/www.xilinx.com\/products\/intellectual-property\/block_memory_generator.html"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2966986.2967011"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021698"}],"event":{"name":"ASPLOS '19: Architectural Support for Programming Languages and Operating Systems","location":"Providence RI USA","acronym":"ASPLOS '19","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304058","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297858.3304058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:15Z","timestamp":1750204395000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304058"}},"subtitle":["FPGA-Accelerated Deep Reinforcement Learning"],"short-title":[],"issued":{"date-parts":[[2019,4,4]]},"references-count":35,"alternative-id":["10.1145\/3297858.3304058","10.1145\/3297858"],"URL":"https:\/\/doi.org\/10.1145\/3297858.3304058","relation":{},"subject":[],"published":{"date-parts":[[2019,4,4]]},"assertion":[{"value":"2019-04-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}