Park: An open platform for learning-augmented computer systems
© 2019 Neural information processing systems foundation. All rights reserved. We present Park, a platform for researchers to experiment with Reinforcement Learning (RL) for computer systems. Using RL for improving the performance of systems has a lot of potential, but is also in many ways very diffe...
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
2021
|
| Online Access: | https://hdl.handle.net/1721.1/132274 |
| _version_ | 1811077193123495936 |
|---|---|
| author | Mao, H Negi, P Narayan, A Wang, H Yang, J Wang, H Marcus, R Addanki, R Khani, M He, S Nathan, V Cangialosi, F Venkatakrishnan, SB Weng, WH Han, S Kraska, T Alizadeh, M |
| author_facet | Mao, H Negi, P Narayan, A Wang, H Yang, J Wang, H Marcus, R Addanki, R Khani, M He, S Nathan, V Cangialosi, F Venkatakrishnan, SB Weng, WH Han, S Kraska, T Alizadeh, M |
| author_sort | Mao, H |
| collection | MIT |
| description | © 2019 Neural information processing systems foundation. All rights reserved. We present Park, a platform for researchers to experiment with Reinforcement Learning (RL) for computer systems. Using RL for improving the performance of systems has a lot of potential, but is also in many ways very different from, for example, using RL for games. Thus, in this work we first discuss the unique challenges RL for systems has, and then propose Park an open extensible platform, which makes it easier for ML researchers to work on systems problems. Currently, Park consists of 12 real world system-centric optimization problems with one common easy to use interface. Finally, we present the performance of existing RL approaches over those 12 problems and outline potential areas of future work. |
| first_indexed | 2024-09-23T10:39:16Z |
| format | Article |
| id | mit-1721.1/132274 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T10:39:16Z |
| publishDate | 2021 |
| record_format | dspace |
| spelling | mit-1721.1/1322742021-09-21T03:48:37Z Park: An open platform for learning-augmented computer systems Mao, H Negi, P Narayan, A Wang, H Yang, J Wang, H Marcus, R Addanki, R Khani, M He, S Nathan, V Cangialosi, F Venkatakrishnan, SB Weng, WH Han, S Kraska, T Alizadeh, M © 2019 Neural information processing systems foundation. All rights reserved. We present Park, a platform for researchers to experiment with Reinforcement Learning (RL) for computer systems. Using RL for improving the performance of systems has a lot of potential, but is also in many ways very different from, for example, using RL for games. Thus, in this work we first discuss the unique challenges RL for systems has, and then propose Park an open extensible platform, which makes it easier for ML researchers to work on systems problems. Currently, Park consists of 12 real world system-centric optimization problems with one common easy to use interface. Finally, we present the performance of existing RL approaches over those 12 problems and outline potential areas of future work. 2021-09-20T18:21:36Z 2021-09-20T18:21:36Z 2021-01-11T16:20:24Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/132274 en https://papers.nips.cc/paper/2019/hash/f69e505b08403ad2298b9f262659929a-Abstract.html Advances in Neural Information Processing Systems Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Neural Information Processing Systems (NIPS) |
| spellingShingle | Mao, H Negi, P Narayan, A Wang, H Yang, J Wang, H Marcus, R Addanki, R Khani, M He, S Nathan, V Cangialosi, F Venkatakrishnan, SB Weng, WH Han, S Kraska, T Alizadeh, M Park: An open platform for learning-augmented computer systems |
| title | Park: An open platform for learning-augmented computer systems |
| title_full | Park: An open platform for learning-augmented computer systems |
| title_fullStr | Park: An open platform for learning-augmented computer systems |
| title_full_unstemmed | Park: An open platform for learning-augmented computer systems |
| title_short | Park: An open platform for learning-augmented computer systems |
| title_sort | park an open platform for learning augmented computer systems |
| url | https://hdl.handle.net/1721.1/132274 |
| work_keys_str_mv | AT maoh parkanopenplatformforlearningaugmentedcomputersystems AT negip parkanopenplatformforlearningaugmentedcomputersystems AT narayana parkanopenplatformforlearningaugmentedcomputersystems AT wangh parkanopenplatformforlearningaugmentedcomputersystems AT yangj parkanopenplatformforlearningaugmentedcomputersystems AT wangh parkanopenplatformforlearningaugmentedcomputersystems AT marcusr parkanopenplatformforlearningaugmentedcomputersystems AT addankir parkanopenplatformforlearningaugmentedcomputersystems AT khanim parkanopenplatformforlearningaugmentedcomputersystems AT hes parkanopenplatformforlearningaugmentedcomputersystems AT nathanv parkanopenplatformforlearningaugmentedcomputersystems AT cangialosif parkanopenplatformforlearningaugmentedcomputersystems AT venkatakrishnansb parkanopenplatformforlearningaugmentedcomputersystems AT wengwh parkanopenplatformforlearningaugmentedcomputersystems AT hans parkanopenplatformforlearningaugmentedcomputersystems AT kraskat parkanopenplatformforlearningaugmentedcomputersystems AT alizadehm parkanopenplatformforlearningaugmentedcomputersystems |