Closed javiarrobas closed 3 years ago
There is a typo on the implementation of the PPO2 algorithm:
https://github.com/ibpsa/project1-boptest-gym/blob/b4b092f00aa73af9445e7f8906d9b7eeed3103fe/examples/train_PPO2.py#L72
That line should load and not save the model. Because of this, the pre-trained model was probably overwriten and lost and therefore the agent needs to be re-trained and references for this example need to be updated.
load
save
There is a typo on the implementation of the PPO2 algorithm:
https://github.com/ibpsa/project1-boptest-gym/blob/b4b092f00aa73af9445e7f8906d9b7eeed3103fe/examples/train_PPO2.py#L72
That line should
loadand notsavethe model. Because of this, the pre-trained model was probably overwriten and lost and therefore the agent needs to be re-trained and references for this example need to be updated.