danijar/embodied

Fast reinforcement learning research

51
/ 100
Established

This project helps reinforcement learning researchers rapidly develop and test new AI agents. You provide your agent's logic and the environments it will interact with. The system then evaluates how well your agent learns and performs, allowing you to iterate on your research faster and at a larger scale. This is for AI researchers and practitioners focused on agent development and experimental evaluation.

No commits in the last 6 months. Available on PyPI.

Use this if you are an AI researcher building and evaluating new reinforcement learning agents and need a standardized, efficient framework for testing across various environments.

Not ideal if you are looking for pre-trained agents for a specific task or a simple library to apply existing reinforcement learning algorithms without developing new ones.

AI-research reinforcement-learning agent-development experimental-design machine-learning
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 25 / 25
Community 18 / 25

How are scores calculated?

Stars

61

Forks

16

Language

Python

License

MIT

Last pushed

Dec 07, 2024

Commits (30d)

0

Get this data via API

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

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