TJU-DRL-LAB/AI-Optimizer
The next generation deep reinforcement learning tookit
This toolkit helps engineers and researchers design AI systems where multiple agents learn to cooperate or compete. It takes diverse data from multi-agent scenarios, such as gameplays or robotic sensor readings, and produces high-performing AI models that can achieve complex goals like coordinating autonomous vehicles or mastering strategy games. It's designed for machine learning engineers, AI researchers, and data scientists working on advanced AI applications.
3,462 stars. No commits in the last 6 months.
Use this if you need to develop AI systems where multiple independent agents interact and learn to achieve a shared or individual objective, especially in complex, real-world environments like robotics, gaming, or logistics.
Not ideal if your problem involves a single AI agent learning in isolation or if you require algorithms that strictly avoid any new data collection during the learning process.
Stars
3,462
Forks
597
Language
Python
License
—
Category
Last pushed
Jun 16, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TJU-DRL-LAB/AI-Optimizer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
robotology/yarp
YARP - Yet Another Robot Platform
HumanCompatibleAI/overcooked_ai
A benchmark environment for fully cooperative human-AI performance.
opendr-eu/opendr
A modular, open and non-proprietary toolkit for core robotic functionalities by harnessing deep learning
shogun-toolbox/shogun
ShÅgun
arturbac/kdevcxx_with_ai
KDevelop and Kate plugins using OpenAI API to assist with code development