{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:23:39Z","timestamp":1788891819611,"version":"build-2803163510"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:00:00Z","timestamp":1727049600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:00:00Z","timestamp":1727049600000},"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":[[2024,9,23]]},"DOI":"10.1109\/hpec62836.2024.10938514","type":"proceedings-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T19:07:19Z","timestamp":1743707239000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Experiences with VITIS AI for Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Nabayan","family":"Chaudhury","sequence":"first","affiliation":[{"name":"Virginia Tech,Department of CS,Blacksburg,VA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atharva","family":"Gondhalekar","sequence":"additional","affiliation":[{"name":"Virginia Tech,Department of ECE,Blacksburg,VA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wu-Chun","family":"Feng","sequence":"additional","affiliation":[{"name":"Virginia Tech,Departments of CS and ECE,Blacksburg,VA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2018.8441797"},{"issue":"2","key":"ref2","first-page":"1543","article-title":"Survey on reinforcement learning for language processing","volume-title":"Artificial Intelligence Review","volume":"56","author":"Uc-Cetina","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SoutheastCon44009.2020.9368267"},{"issue":"1","key":"ref4","article-title":"Sparsity in deep learning: pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler","year":"2021","journal-title":"J. Mach. Learn. Res"},{"key":"ref5","article-title":"Optimizing Deep Learning for Biomedical Imagin","volume-title":"International Conference on Computational Advances in Bio and medical Sciences","author":"Chaturvedi"},{"key":"ref6","volume-title":"In value-based deep reinforcement learning, a pruned network is a good network","author":"Obando-Ceron","year":"2024"},{"key":"ref7","volume-title":"Vitis AI. Advanced Mirco Devices (AMD)","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref9","volume-title":"Google-Deepmind","year":"2024"},{"key":"ref10","first-page":"16509","article-title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Wen","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2018.8445099"},{"key":"ref12","article-title":"GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning","volume-title":"Conference on Robot Learning, 2018","author":"Liang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC54503.2022.9720794"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363622"},{"key":"ref15","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"issue":"7540","key":"ref16","first-page":"529","article-title":"Human-level control through deep reinforcement learning","volume-title":"Nature","volume":"518","author":"Mnih","year":"2015"},{"key":"ref17","article-title":"Actor-critic algorithms","volume-title":"Advances in Neural Information Processing Systems","volume":"12","author":"Konda","year":"1999"},{"key":"ref18","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"ICML","volume":"80","author":"Haarnoja","year":"2018"},{"key":"ref19","volume":"abs\/2005.01643","author":"Levine","year":"2020","journal-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems"},{"key":"ref20","article-title":"Conservative q-learning for offline reinforcement learning","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Kumar","year":"2020"},{"key":"ref21","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International Conference on Machine Learning","author":"Fujimoto","year":"2018"},{"key":"ref22","article-title":"Proximal policy optimization algorithms","volume-title":"CoRR","volume":"abs\/1707.06347","author":"Schulman","year":"2017"},{"key":"ref23","article-title":"Continuous control with deep reinforcement learning","volume-title":"ICLR","author":"Lillicrap","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3387168.3387199"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref26","volume-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref27","volume-title":"ultralytics\/yolov5: v3.1 - Bug Fixes and Performance Improvements","author":"Jocher","year":"2020"},{"key":"ref28","article-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems","volume-title":"2015, software available from tensorflow.org","author":"Abadi"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC54503.2022.9720794"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICIST52614.2021.9440554"},{"issue":"2","key":"ref31","article-title":"Embedded object detection with custom littlenet, finn and vitis ai dcnn accelerators","volume-title":"Journal of Low Power Electronics and Applications","volume":"12","author":"Machura","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3305264"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363622"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"issue":"268","key":"ref35","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume-title":"Journal of Machine Learning Research","volume":"22","author":"Raffin","year":"2021"}],"event":{"name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","location":"Wakefield, MA, USA","start":{"date-parts":[[2024,9,23]]},"end":{"date-parts":[[2024,9,27]]}},"container-title":["2024 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10938401\/10938415\/10938514.pdf?arnumber=10938514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T08:17:48Z","timestamp":1743754668000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10938514\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,23]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/hpec62836.2024.10938514","relation":{},"subject":[],"published":{"date-parts":[[2024,9,23]]}}}