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
16.93k stars 4.14k forks source link

How can I train an existing model? #3215

Closed MasterNoob77 closed 4 years ago

MasterNoob77 commented 4 years ago

Hello,

does anyone know how I train an existing model? With this statement: mlagents-learn <trainer-config-file> --run-id=<run-identifier> --train I will get a new model, but how can I train the same model i.e. two days later again? Thank you for your help, MasterNoob

xiaomaogy commented 4 years ago

You could use --load option.

MasterNoob77 commented 4 years ago

Hey xiaomaogy, thanks for your reply! So instead of --train, --load, and do I have to name the model? mlagents-learn <trainer-config-file> --run-id=<run-identifier> --load this would be correct?

xiaomaogy commented 4 years ago

You could refer to https://github.com/Unity-Technologies/ml-agents/blob/ac4b1a4b91b48cf498c17913b9a68222208a9661/docs/Training-ML-Agents.md for more details. You don't need to name the model.

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.