Tianshou: A Highly Modularized Deep Reinforcement Learning Library

被引：0

作者：

Weng, Jiayi ^{[1
]}

Chen, Huayu ^{[1
]}

Yan, Dong ^{[1
]}

You, Kaichao ^{[2
]}

Duburcq, Alexis ^{[3
]}

Zhang, Minghao ^{[2
]}

Su, Yi ^{[4
]}

Su, Hang ^{[1
]}

Zhu, Jun ^{[1
]}

机构：

[1] Dept. of Comp. Sci. & Tech., BNRist Center, Institute for AI, Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University, Beijing,100084, China

[2] School of Software, Tsinghua University, Beijing,100084, China

[3] Wandercraft, 88 Rue de Rivoli, Paris,75004, France

[4] Ant Group, 525 Almanor Ave, Sunnyvale,CA,94085, United States

来源：

Journal of Machine Learning Research | 2022年 / 23卷

基金：

中国国家自然科学基金;

关键词：

Benchmarking - Deep learning - [!text type='Python']Python[!/text;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

In this paper, we present Tianshou, a highly modularized Python library for deep reinforcement learning (DRL) that uses PyTorch as its backend. Tianshou intends to be research-friendly by providing a flexible and reliable infrastructure of DRL algorithms. It supports online and offline training with more than 20 classic algorithms through a unified interface. To facilitate related research and prove Tianshou’s reliability, we have released Tianshou’s benchmark of MuJoCo environments, covering eight classic algorithms with state-of-the-art performance. We open-sourced Tianshou at https://github.com/thu-ml/tianshou/. ©2022 Jiayi Weng, Huayu Chen, Dong Yan, Kaichao You, Alexis Duburcq, Minghao Zhang, Yi Su, Hang Su and Jun Zhu.

引用

共 50 条

[1] Tianshou: A Highly Modularized Deep Reinforcement Learning Library
Weng, Jiayi
Chen, Huayu
Yan, Dong
You, Kaichao
Duburcq, Alexis
Zhang, Minghao
Su, Yi
Su, Hang
Zhu, Jun
[J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2022, 23
[2] ChainerRL: A Deep Reinforcement Learning Library
Fujita, Yasuhiro
Nagarajan, Prabhat
Kataoka, Toshiki
Ishikawa, Takahiro
[J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2021, 22 : 1 - 14
[3] ChainerRL: A deep reinforcement learning library
Fujita, Yasuhiro
Nagarajan, Prabhat
Kataoka, Toshiki
Ishikawa, Takahiro
[J]. Journal of Machine Learning Research, 2021, 22
[4] CORL: Research-oriented Deep Offline Reinforcement Learning Library
Tarasov, Denis
Nikulin, Alexander
Akimov, Dmitry
Kurenkov, Vladislav
Kolesnikov, Sergey
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
[5] d3rlpy: An Offline Deep Reinforcement Learning Library
Seno, Takuma
Imai, Michita
[J]. Journal of Machine Learning Research, 2022, 23
[6] Conformer-RL: A deep reinforcement learning library for conformer generation
Jiang, Runxuan
Gogineni, Tarun
Kammeraad, Joshua
He, Yifei
Tewari, Ambuj
Zimmerman, Paul M.
[J]. JOURNAL OF COMPUTATIONAL CHEMISTRY, 2022, 43 (27) : 1880 - 1886
[7] Beacon, a Lightweight Deep Reinforcement Learning Benchmark Library for Flow Control
Viquerat, Jonathan
Meliga, Philippe
Jeken-Rico, Pablo
Hachem, Elie
[J]. APPLIED SCIENCES-BASEL, 2024, 14 (09):
[8] RL-X: A Deep Reinforcement Learning Library (Not Only) for RoboCup
Bohlinger, Nico
Dorer, Klaus
[J]. ROBOCUP 2023: ROBOT WORLD CUP XXVI, 2024, 14140 : 228 - 239
[9] A survey on deep learning and deep reinforcement learning in robotics with a tutorial on deep reinforcement learning
Morales, Eduardo F.
Murrieta-Cid, Rafael
Becerra, Israel
Esquivel-Basaldua, Marco A.
[J]. INTELLIGENT SERVICE ROBOTICS, 2021, 14 (05) : 773 - 805
[10] A survey on deep learning and deep reinforcement learning in robotics with a tutorial on deep reinforcement learning
Eduardo F. Morales
Rafael Murrieta-Cid
Israel Becerra
Marco A. Esquivel-Basaldua
[J]. Intelligent Service Robotics, 2021, 14 : 773 - 805

← 1 2 3 4 5 →