davifebba

Thanks for replying! Could you please advise on how to check if all the arms are in-sample? From another run of the script above, I have this data frame below:...

Hi @mgrange1998 ! 1. Yes, it works with only temperature, and even with time using `ax.client.get_next_trial(fixed_features=FixedFeatures({'time':time.time()-start_time}))` However, the time that goes into FixedFeatures has a -delta_T to the real time...

Exactly, time in this case would be a "contextual" variable. Since we cannot control time, the model would suggest only temperature points, but also use time to make predictions. In...

@Balandat, any guidance or example on how to implement that would be very appreciated!

Hi @sdaulton! Thanks for the help! So, what I want to accomplish in the end is to use temperature and time as independent variables to predict device performance. In this...

Hi @sdaulton ! The code below still gives me an error: ``` \ax\core\parameter.py", line 304, in _validate_range_param raise UserInputError( ax.exceptions.core.UserInputError: Upper bound of start_time must be strictly larger than lower.Got:...

Hi @lena-kashtelyan! Sure! Here's a complete example of what I'm trying to do. In this case I simulated the device's response as a function of time, temperature and gas concentration....

No worries. This is not an issue anymore. Thanks!