offlinerl-lib
Benchmarked implementations of Offline RL Algorithms.
Science Score: 54.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (7.3%) to scientific vocabulary
Keywords
Repository
Benchmarked implementations of Offline RL Algorithms.
Basic Info
Statistics
- Stars: 72
- Watchers: 2
- Forks: 7
- Open Issues: 4
- Releases: 2
Topics
Metadata Files
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) orenv(for online experiments). - Available Runs
- Offline:
- TD7 :chartwithupwards_trend:
- XQL :chartwithupwards_trend:
- InAC :chartwithupwards_trend:
- AWAC :chartwithupwards_trend:
- IQL :chartwithupwards_trend:
- TD3BC :chartwithupwards_trend:
- Decision Transformer :chartwithupwards_trend:
- Online Runs
- SAC :chartwithupwards_trend:
- TD3 :chartwithupwards_trend:
- TD7 :chartwithupwards_trend:
- XSAC :chartwithupwards_trend:
Citing OfflineRL-Lib
If you use OfflineRL-Lib in your work, please use the following bibtex
tex
@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.
Owner
- Name: LAMDA-RL
- Login: LAMDA-RL
- Kind: organization
- Repositories: 3
- Profile: https://github.com/LAMDA-RL
Citation (CITATION.cff)
cff-version: 1.2.0 message: "If you use this repository, please cite it as below." authors: - family-names: "Gao" given-names: "Chen-Xiao" - family-names: "Rui" given-names: "Kong" title: "OfflineRL-Lib: Benchmarked Implementations of Offline RL Algorithms" version: 0.1.5 date-released: 2023-02-13 url: "https://github.com/typoverflow/OfflineRL-Lib"
GitHub Events
Total
- Create event: 1
- Commit comment event: 1
- Issues event: 1
- Watch event: 13
- Issue comment event: 1
- Push event: 17
Last Year
- Create event: 1
- Commit comment event: 1
- Issues event: 1
- Watch event: 13
- Issue comment event: 1
- Push event: 17
Committers
Last synced: 10 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| typoverflow | t****w@o****m | 112 |
| LyndonKong | k****n@o****m | 2 |
Issues and Pull Requests
Last synced: 11 months ago
All Time
- Total issues: 6
- Total pull requests: 16
- Average time to close issues: 1 day
- Average time to close pull requests: 1 day
- Total issue authors: 4
- Total pull request authors: 3
- Average comments per issue: 1.67
- Average comments per pull request: 0.06
- Merged pull requests: 13
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 2
- Pull requests: 0
- Average time to close issues: about 3 hours
- Average time to close pull requests: N/A
- Issue authors: 2
- Pull request authors: 0
- Average comments per issue: 1.5
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- typoverflow (3)
- maskillj (1)
- daihuiao (1)
- yunqianevergarden (1)
Pull Request Authors
- typoverflow (12)
- LyndonKong (2)
- OrangeX4 (1)
Top Labels
Issue Labels
Pull Request Labels
Dependencies
- actions/checkout v3 composite
- actions/download-artifact v3 composite
- actions/setup-python v2 composite
- actions/upload-artifact v3 composite
- pypa/gh-action-pypi-publish release/v1 composite
- UtilsRL *
- gym >=0.23.1,<=0.24.1
- numpy *
- pandas *
- torch *
- tqdm *