{"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/tensorflow-agents-efficient-batched","title":"TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow","arxiv_id":"1709.02878","date":"2017-09-08","proceeding":null,"authors":["Danijar Hafner","James Davidson","Vincent Vanhoucke"],"abstract":"We introduce TensorFlow Agents, an efficient infrastructure paradigm for\nbuilding parallel reinforcement learning algorithms in TensorFlow. We simulate\nmultiple environments in parallel, and group them to perform the neural network\ncomputation on a batch rather than individual observations. This allows the\nTensorFlow execution engine to parallelize computation, without the need for\nmanual synchronization. Environments are stepped in separate Python processes\nto progress them in parallel without interference of the global interpreter\nlock. As part of this project, we introduce BatchPPO, an efficient\nimplementation of the proximal policy optimization algorithm. By open sourcing\nTensorFlow Agents, we hope to provide a flexible starting point for future\nprojects that accelerates future research in the field.","url_abs":"http://arxiv.org/abs/1709.02878v2","url_pdf":"http://arxiv.org/pdf/1709.02878v2.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":"tensorflow-agents-efficient-batched","repo_url":"https://github.com/brain-research/batch-ppo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"tensorflow-agents-efficient-batched","repo_url":"https://github.com/vermashresth/damage-sim-tf-agents","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}