danijar/crafter

Benchmarking the Spectrum of Agent Capabilities

56
/ 100
Established

This project offers an open-world survival game environment designed for researchers and engineers developing AI agents. It allows you to put your agent through a variety of tasks like foraging, building, and fighting, providing metrics on how well your agent achieves specific goals. You feed in your AI agent and get out detailed performance statistics on its capabilities.

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

Use this if you are a machine learning researcher or engineer developing and evaluating the general capabilities of reinforcement learning or unsupervised AI agents in a complex, goal-oriented environment.

Not ideal if you are looking for a game to play for entertainment, or if your AI agent is not designed for general-purpose exploration and survival tasks.

reinforcement-learning agent-evaluation AI-benchmarking unsupervised-learning robotics-simulation
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

527

Forks

87

Language

Python

License

MIT

Last pushed

Jan 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/danijar/crafter"

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