-
Notifications
You must be signed in to change notification settings - Fork 151
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
How do I save a trained model to reuse it? #69
Comments
During training, the agent model is saved through the rl-agents/rl_agents/trainer/evaluation.py Line 276 in a290be3
There are two cases where this function is used to automatically save the model in rl-agents/rl_agents/trainer/evaluation.py Line 318 in a290be3
The resulting models are saved as .tar files, by default both in the run directory and in an Then, in order to load a save model, you just have to use the |
Thank you for your reply. What should I do to recover the agent to be used outside of evaluation or experiments? For example, I want to run this snippet locally:
|
Oh, I see! Then you can just use |
I specifically want to save the DQN network i've been working on. I went through the documentation and can't find anything. I tried using pickle for my agent after training but that doesn't seem to work either. I'd appreciate any input.
The text was updated successfully, but these errors were encountered: