TY - JOUR
T1 - d3rlpy
T2 - An Offline Deep Reinforcement Learning Library
AU - Seno, Takuma
AU - Imai, Michita
N1 - Funding Information:
This work is supported by Information-technology Promotion Agency, Japan (IPA), Exploratory IT Human Resources Project (MITOU Program) in the fiscal year 2020. We would like to express our genuine gratitude for the contributions made by the voluntary contributors. We would also like to thank our users who have provided constructive feedback and insights.
Publisher Copyright:
©2022 Takuma Seno and Michita Imai.
PY - 2022/10/1
Y1 - 2022/10/1
N2 - In this paper, we introduce d3rlpy, an open-sourced offline deep reinforcement learning (RL) library for Python. d3rlpy supports a set of offline deep RL algorithms as well as off-policy online algorithms via a fully documented plug-and-play API. To address a reproducibility issue, we conduct a large-scale benchmark with D4RL and Atari 2600 dataset to ensure implementation quality and provide experimental scripts and full tables of results. The d3rlpy source code can be found on GitHub: https://github.com/takuseno/d3rlpy.
AB - In this paper, we introduce d3rlpy, an open-sourced offline deep reinforcement learning (RL) library for Python. d3rlpy supports a set of offline deep RL algorithms as well as off-policy online algorithms via a fully documented plug-and-play API. To address a reproducibility issue, we conduct a large-scale benchmark with D4RL and Atari 2600 dataset to ensure implementation quality and provide experimental scripts and full tables of results. The d3rlpy source code can be found on GitHub: https://github.com/takuseno/d3rlpy.
KW - deep reinforcement learning
KW - offline reinforcement learning
KW - open source software
KW - pytorch
KW - reproducibility
UR - http://www.scopus.com/inward/record.url?scp=85148110345&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85148110345&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:85148110345
SN - 1532-4435
VL - 23
JO - Journal of Machine Learning Research
JF - Journal of Machine Learning Research
M1 - 315
ER -