README.md

OfflineRL-Lib

OfflineRL-Lib provides unofficial and benchmarked PyTorch implementations for selected OfflineRL algorithms, including:

• In-Sample Actor Critic (InAC)
• Extreme Q-Learning (XQL)
• Implicit Q-Learning (IQL)
• Decision Transformer (DT)
• Advantage-Weighted Actor Critic (AWAC)
• TD3-BC
• TD7

For Model-Based algorithms, please check OfflineRL-Kit!

Benchmark Results

• We benchmark and visualize the result via WandB. Click the following WandB links, and group the runs via the entry task (for offline experiments) or env (for online experiments).
• Available Runs
  • Offline:
    • TD7 📈
    • XQL 📈
    • InAC 📈
    • AWAC 📈
    • IQL 📈
    • TD3BC 📈
    • Decision Transformer 📈
  • Online Runs
    • SAC 📈
    • TD3 📈
    • TD7 📈
    • XSAC 📈

Citing OfflineRL-Lib

If you use OfflineRL-Lib in your work, please use the following bibtex

@software{
  offlinerllib,
  author = {Gao, Chen-Xiao and Rui, Kong},
  month = feb,
  title = {{OfflineRL-Lib: Benchmarked Implementations of Offline RL Algorithms}},
  url = {https://github.com/typoverflow/OfflineRL-Lib},
  version = {0.1.5},
  year = {2023}
}

Acknowledgements

We thank CORL for providing finetuned hyper-parameters.