decision-diffuser
decision-diffuser copied to clipboard
Metrics about hopper-medium-v2
hello, when I train and eval the model in hopper-medium-v2 task.
I got results below:
{'average_ep_reward': 3269.0621404844796, 'std_ep_reward': 679.6445333781064}
But in paper, I see the metirc value in the table1 is 107.2
Can you explain what's the metric in the table1 and whether the result {'average_ep_reward': 3269.0621404844796, 'std_ep_reward': 679.6445333781064} is consistent with the performace in the paper. Thanks very much.
I think metric in paper is normalized score which can be obtained by using gym env