Idea: Using ML-agent to replicate Tensorflow Playground in Unity

Unity-Technologies / ml-agents

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.

https://unity.com/products/machine-learning-agents

Other

16.98k stars 4.14k forks source link

Idea: Using ML-agent to replicate Tensorflow Playground in Unity #68

Closed Hackathorn closed 6 years ago

Hackathorn commented 6 years ago

Just getting into TF by taking Ng's Deep Neural Net courses. TF Playground has been useful for intuition. Been experimenting with scikit-Learn and Unity. What about using ML-agent to replicate Tensorflow Playground in Unity? Doable? Useful?

So, is this a good idea as a project for learning ML-agent? Any hints on how to proceed? Anyone interested in collaborating? How can we leverage rendering power of Unity to understand DNN dynamics?

Hackathorn commented 6 years ago

After thinking about my question, there is a mismatch of purpose. First, I need to understand more about RL. Sorry...

lock[bot] commented 4 years ago

This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.