macop.callbacks.policies

UCB policy Checkpoint class implementation

Classes

UCBCheckpoint(every, filepath)

UCB checkpoint is used for loading previous Upper Confidence Bound data and start again after loading checkpoint Need to be the same operators used during previous run (see macop.policies.reinforcement.UCBPolicy for more details)

class macop.callbacks.policies.UCBCheckpoint(every, filepath)

UCB checkpoint is used for loading previous Upper Confidence Bound data and start again after loading checkpoint Need to be the same operators used during previous run (see macop.policies.reinforcement.UCBPolicy for more details)

algo

{Algorithm} – main algorithm instance reference

every

{int} – checkpoint frequency used (based on number of evaluations)

filepath

{str} – file path where checkpoints will be saved

load()

Load backup lines as rewards and occurrences for UCB

run()

Check if necessary to do backup based on every variable