Unity-Technologies/obstacle-tower-env
Obstacle Tower Environment
Provides a procedurally generated multi-floor platforming environment built in Unity that combines vision, locomotion, and planning challenges with configurable difficulty scaling and visual themes. Exposes a Python API via OpenAI Gym wrapper that communicates with pre-compiled binaries (auto-downloaded per platform), integrating with ML-Agents 1.x for reinforcement learning workflows. Features up to 100 floors with randomized room layouts, puzzles, and enemy types to test agent generalization across unseen environment combinations.
545 stars and 11 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
545
Forks
123
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 29, 2020
Monthly downloads
11
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.
Related frameworks
UnityTechnologies/MachineLearningRoguelike
A small Roguelike game that uses Machine Learning to power its entities. Originally used in...
CoderOneHQ/ultimate-volleyball
3D RL Volleyball environment built on Unity ML-Agents
kaiergin/runescape-ML
Train computer vision models to complete clicking tasks by learning from your recorded data
smtmRadu/DeepUnity
An open source deep learning library for Unity.
Naton1/osrs-pvp-reinforcement-learning
Train a neural network to PvP in Old School RuneScape using reinforcement learning.