danijar/diamond_env

Standardized Minecraft Diamond Environment for Reinforcement Learning

35
/ 100
Emerging

This project provides a standardized virtual environment for training AI agents to play Minecraft. It simulates the complex task of starting in a randomly generated world and progressing through milestones to collect a diamond. Researchers in reinforcement learning use this to test and compare algorithms that learn from sparse rewards and generalize across varied game environments.

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

Use this if you are a reinforcement learning researcher developing AI agents that need to learn complex sequential tasks in dynamic, open-ended environments without human supervision or predefined steps.

Not ideal if you need an environment with dense rewards, simpler tasks, or if your primary focus is on supervised learning from existing human gameplay data.

reinforcement-learning-research game-AI minecraft-agent-training AI-benchmarking exploration-challenge
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 3 / 25

How are scores calculated?

Stars

37

Forks

1

Language

Python

License

MIT

Category

unreal-engine-ml

Last pushed

May 19, 2023

Commits (30d)

0

Get this data via API

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

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