{"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/rllib-abstractions-for-distributed","title":"RLlib: Abstractions for Distributed Reinforcement Learning","arxiv_id":"1712.09381","date":"2017-12-26","proceeding":"ICML 2018 7","authors":["Eric Liang","Richard Liaw","Philipp Moritz","Robert Nishihara","Roy Fox","Ken Goldberg","Joseph E. Gonzalez","Michael. I. Jordan","Ion Stoica"],"abstract":"Reinforcement learning (RL) algorithms involve the deep nesting of highly\nirregular computation patterns, each of which typically exhibits opportunities\nfor distributed computation. We argue for distributing RL components in a\ncomposable way by adapting algorithms for top-down hierarchical control,\nthereby encapsulating parallelism and resource requirements within\nshort-running compute tasks. We demonstrate the benefits of this principle\nthrough RLlib: a library that provides scalable software primitives for RL.\nThese primitives enable a broad range of algorithms to be implemented with high\nperformance, scalability, and substantial code reuse. RLlib is available at\nhttps://rllib.io/.","url_abs":"http://arxiv.org/abs/1712.09381v4","url_pdf":"http://arxiv.org/pdf/1712.09381v4.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":"rllib-abstractions-for-distributed","repo_url":"https://github.com/ray-project/ray","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rllib-abstractions-for-distributed","repo_url":"https://github.com/AmeerHajAli/ray2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"rllib-abstractions-for-distributed","repo_url":"https://github.com/susumuota/distributed_experience_replay","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"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"},{"task_slug":"rllib","task_name":"rllib"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.09381","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}