Chapter 04

Deep Reinforcement Learning System

For now, this category only contains system for drl papers and projects.

Mao, Hongzi, et al. "Park: An Open Platform for Learning-Augmented Computer Systems." Advances in Neural Information Processing Systems. 2019.
Summary: This work builds a platform to introduce DRL to computer system optimizaton. It provides a lot of APIs so researcher can focus on developing algorithm rather spend a lot of time on writing system engineering codes.
Ray: A Distributed Framework for Emerging {AI} Applications(https://www.usenix.org/conference/osdi18/presentation/moritz)
- Moritz, Philipp, et al. (OSDI 2018)
- Summary: Distributed DRL training, simulation and inference system. Can be used as a high-performance python framework.
Elf: An extensive, lightweight and flexible research platform for real-time strategy games(https://papers.nips.cc/paper/6859-elf-an-extensive-lightweight-and-flexible-research-platform-for-real-time-strategy-games.pdf)(https://github.com/facebookresearch/ELF)
- Tian, Yuandong, Qucheng Gong, Wenling Shang, Yuxin Wu, and C. Lawrence Zitnick. (NIPS 2017)
- Summary:
Horizon: Facebook's Open Source Applied Reinforcement Learning Platform(https://arxiv.org/pdf/1811.00260)(https://github.com/facebookresearch/Horizon)
- Gauci, Jason, et al. (preprint 2019)
RLgraph: Modular Computation Graphs for Deep Reinforcement Learning(http://www.sysml.cc/doc/2019/43.pdf)(https://github.com/rlgraph/rlgraph)
- Schaarschmidt, Michael, Sven Mika, Kai Fricke, and Eiko Yoneki. (SysML 2019)
- Summary:
Stable-Baselines: Stable-Baselines3: Reliable Reinforcement Learning Implementations 2021 -(https://www.jmlr.org/papers/volume22/20-1364/20-1364.pdf)(https://github.com/hill-a/stable-baselines)

Chapter 04

Deep Reinforcement Learning System

For now, this category only contains system for drl papers and projects.

Mao, Hongzi, et al. "Park: An Open Platform for Learning-Augmented Computer Systems." Advances in Neural Information Processing Systems. 2019.
Summary: This work builds a platform to introduce DRL to computer system optimizaton. It provides a lot of APIs so researcher can focus on developing algorithm rather spend a lot of time on writing system engineering codes.
Ray: A Distributed Framework for Emerging {AI} Applications(https://www.usenix.org/conference/osdi18/presentation/moritz)
- Moritz, Philipp, et al. (OSDI 2018)
- Summary: Distributed DRL training, simulation and inference system. Can be used as a high-performance python framework.
Elf: An extensive, lightweight and flexible research platform for real-time strategy games(https://papers.nips.cc/paper/6859-elf-an-extensive-lightweight-and-flexible-research-platform-for-real-time-strategy-games.pdf)(https://github.com/facebookresearch/ELF)
- Tian, Yuandong, Qucheng Gong, Wenling Shang, Yuxin Wu, and C. Lawrence Zitnick. (NIPS 2017)
- Summary:
Horizon: Facebook's Open Source Applied Reinforcement Learning Platform(https://arxiv.org/pdf/1811.00260)(https://github.com/facebookresearch/Horizon)
- Gauci, Jason, et al. (preprint 2019)
RLgraph: Modular Computation Graphs for Deep Reinforcement Learning(http://www.sysml.cc/doc/2019/43.pdf)(https://github.com/rlgraph/rlgraph)
- Schaarschmidt, Michael, Sven Mika, Kai Fricke, and Eiko Yoneki. (SysML 2019)
- Summary:
Stable-Baselines: Stable-Baselines3: Reliable Reinforcement Learning Implementations 2021 -(https://www.jmlr.org/papers/volume22/20-1364/20-1364.pdf)(https://github.com/hill-a/stable-baselines)