I have tried to use the agent.restore(“path to checkpoint”) and then continue training with tune.run(self.agent,…hyperparameters here). I do get a message logged to the console telling me that my agent has been restored, but it seems to create a new directory (i.e. experiment with it’s own metadata)…

How to restore a trained agent to further train it?

Lars_Simon_Zehnder July 29, 2021, 5:51pm 3

maybe this helps you with your problem.

Simon

1 Like