{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:24:31Z","timestamp":1730265871013,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191108","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["FastAct: A Lightweight Actor Compression Framework for Fast Policy Learning"],"prefix":"10.1109","author":[{"given":"Hongjie","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science, Sichuan Normal University,Chengdu,China"}]},{"given":"Haoming","family":"Ma","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,Guangzhou,China"}]},{"given":"Zhenyu","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan Normal University,Chengdu,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref2","first-page":"621","article-title":"Towards playing full moba games with deep reinforcement learning","volume":"33","author":"Ye","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","article-title":"Qlib: An ai-oriented quantitative investment platform","author":"Yang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05172-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04301-9"},{"key":"ref6","first-page":"1407","article-title":"Impala: Scalable dis-tributed deep-rl with importance weighted actor-learner architectures","volume-title":"International conference on machine learning. PMLR","author":"Espeholt"},{"article-title":"Distributed prioritized experience replay","volume-title":"International Conference on Learning Representations","author":"Horgan","key":"ref7"},{"article-title":"Seed rl: Scalable and efficient deep-rl with accelerated central inference","volume-title":"International Conference on Learning Representations","author":"Espeholt","key":"ref8"},{"key":"ref9","first-page":"3053","article-title":"Rllib: Abstractions for distributed reinforcement learning","volume-title":"International Conference on Machine Learning. PMLR","author":"Liang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852451"},{"key":"ref12","article-title":"Efficient transformers in reinforcement learning using actor-learner distillation","volume-title":"International Conference on Learning Representations","author":"Parisotto","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.03.017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01054"},{"key":"ref15","article-title":"Structured pruning is all you need for pruning cnns at initialization","author":"Cai","year":"2022","journal-title":"ar Xiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539266"},{"article-title":"Ga3c: Gpu-based a3c for deep reinforcement learning","volume-title":"30th Conference on Neural Information Processing Systems (NIPS 2016)","author":"Iuri","key":"ref17"},{"key":"ref18","first-page":"1","article-title":"Efficient parallel methods for deep reinforcement learning","volume-title":"The Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM)","author":"Alfredo"},{"key":"ref19","article-title":"Elf: An ex-tensive, lightweight and flexible research platform for real-time strategy games","volume":"30","author":"Tian","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"7652","article-title":"Sample factory: Egocentric 3d control from pixels at 100000 fps with asynchronous reinforcement learning","volume-title":"International Conference on Machine Learning. PMLR","author":"Petrenko"},{"key":"ref21","first-page":"561","article-title":"Ray: A distributed framework for emerging {AI} applications","volume-title":"13th USENIX Sympo-sium on Operating Systems Design and Implementation (OSDI 18)","author":"Moritz"},{"key":"ref22","article-title":"Quarl: Quantization for fast and environmentally sustainable reinforcement learning","author":"Faust","year":"2022","journal-title":"Transactions on Machine Learning Research (TMLR) 2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2363\/1\/012001"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191108.pdf?arnumber=10191108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:29:12Z","timestamp":1705026552000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191108\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191108","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}