{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/reinforcement-learning-through-asynchronous","title":"Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU","arxiv_id":"1611.06256","date":"2016-11-18","proceeding":null,"authors":["Mohammad Babaeizadeh","Iuri Frosio","Stephen Tyree","Jason Clemons","Jan Kautz"],"abstract":"We introduce a hybrid CPU/GPU version of the Asynchronous Advantage\nActor-Critic (A3C) algorithm, currently the state-of-the-art method in\nreinforcement learning for various gaming tasks. We analyze its computational\ntraits and concentrate on aspects critical to leveraging the GPU's\ncomputational power. We introduce a system of queues and a dynamic scheduling\nstrategy, potentially helpful for other asynchronous algorithms as well. Our\nhybrid CPU/GPU version of A3C, based on TensorFlow, achieves a significant\nspeed up compared to a CPU implementation; we make it publicly available to\nother researchers at https://github.com/NVlabs/GA3C .","url_abs":"http://arxiv.org/abs/1611.06256v3","url_pdf":"http://arxiv.org/pdf/1611.06256v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"reinforcement-learning-through-asynchronous","repo_url":"https://github.com/NVlabs/GA3C","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"reinforcement-learning-through-asynchronous","repo_url":"https://github.com/Sheepsody/Batched-Impala-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"reinforcement-learning-through-asynchronous","repo_url":"https://github.com/nicoladainese96/SC2-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"scheduling","task_name":"Scheduling"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"a3c","method_name":"A3C"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.06256","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}