Unity-Technologies/obstacle-tower-env

Obstacle Tower Environment

59
/ 100
Established

The Obstacle Tower Environment helps researchers and developers train and test AI agents in a complex, 3D gaming environment. It takes in an agent's actions and outputs visual observations and game state, allowing for the development of agents capable of vision, locomotion, and strategic planning. This is designed for AI researchers and machine learning engineers working on generalization in reinforcement learning.

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

Use this if you are developing AI agents and need a challenging, procedurally generated environment to test their ability to generalize across different visual layouts, puzzles, and difficulties.

Not ideal if you are looking for a simple, single-task environment or if your primary focus is not on generalization in reinforcement learning.

reinforcement-learning AI-training game-AI generalization-testing procedural-generation
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 24 / 25

How are scores calculated?

Stars

545

Forks

123

Language

Python

License

Apache-2.0

Last pushed

Jul 29, 2020

Commits (30d)

0

Dependencies

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Unity-Technologies/obstacle-tower-env"

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