beyretb/AnimalAI-Olympics
Code repository for the Animal AI Olympics competition
Provides a Unity-based 3D arena environment with 900 cognitive tasks inspired by animal behavior research, where agents interact with spawned objects (rewards/penalties) to develop and test cognitive skills. Extends Unity ML-Agents with dynamic arena reconfiguration between episodes and includes both Gym and ml-agents APIs, plus training libraries implementing PPO and SAC algorithms for agent development.
577 stars. No commits in the last 6 months.
Stars
577
Forks
83
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 27, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/beyretb/AnimalAI-Olympics"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
rentruewang/aioway
AI on the way. An RDBMS approach to deep learning. Declarative, explainable, scalable,...
miguelgfierro/ai_projects
AI projects
danijar/elements
Building blocks for productive research
wikimedia/articlequality
Github mirror - our actual code is hosted with Gerrit (please see...
wikimedia/editquality
Github mirror - our actual code is hosted with Gerrit (please see...