search

UoA-CARES / cares_reinforcement_learning

CARES Reinforcement Learning Package
11 stars 2 forks source link

Update - checkpoint_frequency #142

Closed rainingx683 closed 1 week ago

rainingx683 commented 7 months ago

Currently it means per number of episodes. But it would make sense to change it to how many times we want to save the model? suggest: round((max_steps_training/episode_horizon)/checkpoint_frequency), then replace the current self.checkpoint_frequency with this.

e.g. self.num_ep_for_save = _round((max_steps_training/episode_horizon)/checkpointfrequency) if self.network is not None and self.log_count % self.num_ep_for_save == 0: self.network.save_models( f"{self.algorithm}-checkpoint-{self.log_count}", self.directory )

beardyFace commented 6 months ago

@rainingx683 can you make an adjustment to show exactly what you mean here?

beardyFace commented 1 week ago

resolved with model being saved per evaluation in #218