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
17.26k stars 4.17k forks source link

Imitation Learning: Teacher behavior saved file. #586

Closed icaro56 closed 6 years ago

icaro56 commented 6 years ago

Is there any way to save teacher behavior, and then use the saved file for imitation learning?

awjuliani commented 6 years ago

HI @icaro56,

Currently we only support simultaneous collection and training, but we will soon be adding the ability to save a training dataset, and then train on it at a later time.

icaro56 commented 6 years ago

Thanks @awjuliani

In my research, I need this ability to save a training dataset ...

I also need to implement other versions of imitation learning and inverse reinforcement learning. If I make it, I'll share it with you.

traveltrousers commented 6 years ago

Would also like this....

awjuliani commented 6 years ago

Hi all. Closing this issue due to inactivity. Feel free to reopen it if desired. Also, we are actively working on implementing this feature, so please look forward to it soon.

github-actions[bot] commented 3 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.