{"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/rlgraph-modular-computation-graphs-for-deep","title":"RLgraph: Modular Computation Graphs for Deep Reinforcement Learning","arxiv_id":"1810.09028","date":"2018-10-21","proceeding":null,"authors":["Michael Schaarschmidt","Sven Mika","Kai Fricke","Eiko Yoneki"],"abstract":"Reinforcement learning (RL) tasks are challenging to implement, execute and\ntest due to algorithmic instability, hyper-parameter sensitivity, and\nheterogeneous distributed communication patterns. We argue for the separation\nof logical component composition, backend graph definition, and distributed\nexecution. To this end, we introduce RLgraph, a library for designing and\nexecuting reinforcement learning tasks in both static graph and define-by-run\nparadigms. The resulting implementations are robust, incrementally testable,\nand yield high performance across different deep learning frameworks and\ndistributed backends.","url_abs":"http://arxiv.org/abs/1810.09028v2","url_pdf":"http://arxiv.org/pdf/1810.09028v2.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":"rlgraph-modular-computation-graphs-for-deep","repo_url":"https://github.com/rlgraph/rlgraph","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sensitivity","task_name":"Sensitivity"},{"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}