MeanReward
Macro mean reward: mean over tasks of each task's mean sample reward.
Attributes
attributenamestr= 'mean_reward'Functions
funccompute(self, task_rewards) -> floatparamselfparamtask_rewardsSequence[Sequence[float]]Returns
float
Macro mean reward: mean over tasks of each task's mean sample reward.
attributenamestr= 'mean_reward'funccompute(self, task_rewards) -> floatparamselfparamtask_rewardsSequence[Sequence[float]]Returns
float