NN model not created when agent trained with --env

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

17k stars 4.15k forks source link

NN model not created when agent trained with --env #2004

Closed Irekter closed 5 years ago

Irekter commented 5 years ago

Hey, I am using conda for ML-agents. Whenever I reference a path in --envs and set multiple environments, the agent get trained but the model never gets saved in file. But training in the unity editor using the standard method successfully saves the model to file.

Am iI doing something wrong? Please help me out! Thanks

xiaomaogy commented 5 years ago

Thank you for the discussion. We are closing this issue due to inactivity. Feel free to reopen it if you’d like to continue the discussion though.

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.