oxwhirl / pymarl

Python Multi-Agent Reinforcement Learning framework
Apache License 2.0
1.87k stars 384 forks source link

Running Trained Agents #154

Open andresgr96 opened 1 year ago

andresgr96 commented 1 year ago

Hi there,

Is there a simple command to run already an already trained model, but without learning? I understand I can comment on the training in the code and remove the epsilon greedy action selection to add a selection that always chooses the learned model, but isn't there a straightforward way or command to run a trained model n times to get results for analysis?

DarthVictor508 commented 7 months ago

Also eager to know if there's a solution.