{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/iroko-a-framework-to-prototype-reinforcement","title":"Iroko: A Framework to Prototype Reinforcement Learning for Data Center Traffic Control","arxiv_id":"1812.09975","date":"2018-12-24","proceeding":null,"authors":["Fabian Ruffy","Michael Przystupa","Ivan Beschastnikh"],"abstract":"Recent networking research has identified that data-driven congestion control\n(CC) can be more efficient than traditional CC in TCP. Deep reinforcement\nlearning (RL), in particular, has the potential to learn optimal network\npolicies. However, RL suffers from instability and over-fitting, deficiencies\nwhich so far render it unacceptable for use in datacenter networks. In this\npaper, we analyze the requirements for RL to succeed in the datacenter context.\nWe present a new emulator, Iroko, which we developed to support different\nnetwork topologies, congestion control algorithms, and deployment scenarios.\nIroko interfaces with the OpenAI gym toolkit, which allows for fast and fair\nevaluation of different RL and traditional CC algorithms under the same\nconditions. We present initial benchmarks on three deep RL algorithms compared\nto TCP New Vegas and DCTCP. Our results show that these algorithms are able to\nlearn a CC policy which exceeds the performance of TCP New Vegas on a dumbbell\nand fat-tree topology. We make our emulator open-source and publicly available:\nhttps://github.com/dcgym/iroko","url_abs":"http://arxiv.org/abs/1812.09975v1","url_pdf":"http://arxiv.org/pdf/1812.09975v1.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":"iroko-a-framework-to-prototype-reinforcement","repo_url":"https://github.com/dcgym/iroko","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":"openai-gym","task_name":"OpenAI Gym"},{"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":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"dcgym/iroko","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"77e366a7a9b85a8f0b9a732e642b45d27472643e8858dda120a1a18969ba4ed3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}