d3rlpy: An Offline Deep Reinforcement Learning Library

Takuma Seno, Michita Imai

Research output: Contribution to journalArticlepeer-review

Abstract

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.

Original languageEnglish
Article number315
JournalJournal of Machine Learning Research
Volume23
Publication statusPublished - 2022 Oct 1

Keywords

  • deep reinforcement learning
  • offline reinforcement learning
  • open source software
  • pytorch
  • reproducibility

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'd3rlpy: An Offline Deep Reinforcement Learning Library'. Together they form a unique fingerprint.

Cite this