search

intelligent-environments-lab / CityLearn

Official reinforcement learning environment for demand response and load shaping
MIT License
462 stars 167 forks source link

Question regarding evaluation #36

Closed zxnga closed 1 year ago

zxnga commented 1 year ago

Hello, thanks for providing this environment.

I took part in the 2022 challenge and I am looking at the 2021 environment. I'm confused on the right way to evaluate the agent. In the 2022 challenge we have the env.evaluate() function, in the 2021 environment it seems that the env.cost() method is used to evaluate the agent (from the challenge page), but it doen't seem to exist anymore.

Do we have to use the cost functions in the citylearn.cost_function file and implement our own cost function ?

Thank you !

kingsleynweye commented 1 year ago

@TheoZan, the environment that was used in the CityLearn Challenge 2021 is different from what was used in the CityLearn Challenge 2022.

The CityLearn Challenge 2021 has been archived and can be downloaded here: https://github.com/intelligent-environments-lab/CityLearn/releases/tag/v1.0.0. In this release, you will find the env.cost() function.

If you want to use the same cost function from CityLearn Challenge 2021 in the CityLearn Challenge 2022 environment, they are available in the citylearn.cost_function module and you can calculate by calling the relevant function.

kingsleynweye commented 1 year ago

I am closing out this issue @TheoZan since there has been no response. Please, let me know to reopen if needed.