Laggg/neural-env-surviv

Train environment model for RL based agent in browser-based multiplayer battle royale game «surviv.io»

23
/ 100
Experimental

This project helps game developers and AI researchers create and test AI agents for games without a built-in training environment. It takes game footage and agent actions to predict the next game state and rewards, enabling the training of AI bots. The primary users are those building or researching AI for games, particularly for browser-based multiplayer titles.

No commits in the last 6 months.

Use this if you need to train an AI agent for a game that doesn't offer a dedicated simulation environment, especially for tasks like movement and item collection.

Not ideal if you already have access to a game's native training environment or if your primary goal is to develop human-controlled gameplay.

game-AI reinforcement-learning game-bot-development AI-simulation virtual-environment-creation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

26

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 23, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Laggg/neural-env-surviv"

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