zuoxingdong/lagom

lagom: A PyTorch infrastructure for rapid prototyping of reinforcement learning algorithms.

40
/ 100
Emerging

Lagom helps machine learning researchers quickly build and test reinforcement learning algorithms. It takes your definitions of an RL agent and environment, along with experiment configurations, and outputs trained agents and performance metrics. This tool is designed for ML practitioners and researchers who develop and evaluate new reinforcement learning methods.

378 stars. No commits in the last 6 months.

Use this if you need a balanced, modular framework built on PyTorch to rapidly prototype, test, and parallelize your reinforcement learning algorithms.

Not ideal if you prefer a high-level API that abstracts away most of the reinforcement learning algorithm details or if you don't use PyTorch.

reinforcement-learning machine-learning-research algorithm-prototyping model-training experiment-management
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

378

Forks

31

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 19, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zuoxingdong/lagom"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.