louis030195/prismarine-gym

train minecraft agents using reinforcement learning (inspired by https://gym.openai.com/)

21
/ 100
Experimental

This project allows developers to train AI agents to perform tasks within the Minecraft game environment. It takes in game states as observations and outputs actions for the agent to take, such as moving or interacting with objects. It's used by AI researchers and developers who want to experiment with reinforcement learning in a complex, simulated 3D world.

No commits in the last 6 months.

Use this if you are an AI developer or researcher looking to build, test, and refine reinforcement learning algorithms for agents operating in a Minecraft-like environment.

Not ideal if you are a Minecraft player simply looking for automated gameplay or a non-developer seeking a ready-to-use AI bot.

AI-development reinforcement-learning game-AI agent-training simulated-environments
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

TypeScript

License

MIT

Category

godot-game-ai

Last pushed

Aug 31, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/louis030195/prismarine-gym"

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