{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:26:18Z","timestamp":1759134378806,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T00:00:00Z","timestamp":1605571200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T00:00:00Z","timestamp":1605571200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T00:00:00Z","timestamp":1605571200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,11,17]]},"DOI":"10.1109\/mascots50786.2020.9285940","type":"proceedings-article","created":{"date-parts":[[2020,12,21]],"date-time":"2020-12-21T23:22:16Z","timestamp":1608592936000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["Towards a common environment for learning scheduling algorithms"],"prefix":"10.1109","author":[{"given":"Renato Luiz","family":"de Freitas Cunha","sequence":"first","affiliation":[]},{"given":"Luiz","family":"Chaimowicz","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"RLScheduler Learn to Schedule HPC Batch Jobs Using Deep Reinforcement Learning","year":"2019","author":"zhang","key":"ref32"},{"key":"ref31","first-page":"731","article-title":"Pantheon: the training ground for Internet congestion-control research","author":"yan","year":"0","journal-title":"2018 USENIX Annual Technical Conference ( USENIX ATC 18)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1080\/09540099108946587"},{"key":"ref10","first-page":"3050","article-title":"A deep reinforcement learning perspective on internet congestion control","author":"jay","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref11","first-page":"253","article-title":"Are user runtime estimates inherently inaccurate?","author":"lee","year":"0","journal-title":"Workshop on Job Scheduling Strategies for Parallel Processing"},{"key":"ref12","article-title":"State of the Art Control of Atari Games Using Shallow Reinforcement Learning","author":"liang","year":"2016","journal-title":"AAMAS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5699"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref15","first-page":"2494","article-title":"Park: An open platform for learning-augmented computer systems","author":"mao","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref17","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref19","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","author":"recht","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2006.1639311"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2016.08.010"},{"key":"ref27","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"journal-title":"PowerAI DDL","year":"2017","author":"cho","key":"ref3"},{"key":"ref6","article-title":"Experience with the parallel workloads archive","author":"feitelson","year":"2012","journal-title":"The Hebrew University and the Israel Institute of Technology"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360998"},{"journal-title":"OpenAI Baselines","year":"2017","author":"dhariwal","key":"ref5"},{"key":"ref8","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"0","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3345768.3355908"},{"journal-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref2"},{"key":"ref9","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"0","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2017.09.002"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HUST.2016.006"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"journal-title":"Horovod fast and easy distributed deep learning in tensorflow","year":"2018","author":"sergeev","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref25","first-page":"326","author":"sutton","year":"2018","journal-title":"Reinforcement learning An introduction chapter 13 Policy Gradient Methods"}],"event":{"name":"2020 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)","start":{"date-parts":[[2020,11,17]]},"location":"Nice, France","end":{"date-parts":[[2020,11,19]]}},"container-title":["2020 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9285930\/9285931\/09285940.pdf?arnumber=9285940","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:50:47Z","timestamp":1656453047000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9285940\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,17]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/mascots50786.2020.9285940","relation":{},"subject":[],"published":{"date-parts":[[2020,11,17]]}}}