search

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
17.19k stars 4.16k forks source link

Open multiple environments with python multi processing #1382

Closed imankgoyal closed 5 years ago

imankgoyal commented 6 years ago

Hi, I want to use python multi-processing to open up multiple unity environments. More specifically, I was thinking of modifying ml-agents/ml-agents/mlagents/envs/environment.py function to open up multiple processes with different instantiations of unity, and communicate accordingly. Do you think it is a good way to go? Is there any obvious limitation/bottleneck to this approach? I would very much appreciate any suggestions and advice.

xiaomaogy commented 6 years ago

Hi @imankgoyal, the bottleneck here is how many instance of Unity you can launch in one machine. We are also exploring this approach ourselves.

eshvk commented 5 years ago

Hi @imankgoyal, Thanks for reaching out to us. We will keep you posted once this gets released.

harperj commented 5 years ago

This is a duplicate of #828 and something we're working on for the near future. I'm going to close this issue, but please feel free to continue any related discussion there.

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.