search

VinF / deer

DEEp Reinforcement learning framework
Other
485 stars 126 forks source link

MG two sorages #95

Closed joyandeh closed 1 year ago

joyandeh commented 2 years ago

hello dear Vincent, Thank you so much for your precious work, it is so helpful and practical for me. I have some questions about micro gride two storages. For my data it's a time consuming process about 53 minutes for each epoch, and every time that I want to do some little tuning, I must run it again (with a new untrained network). Is it possible to save and use the trained network in a new training epoch?

Thank you Erfan

VinF commented 1 year ago

Dear Erfan,

Sorry for tis very late reply. I missed the notification and see this while checking the remaining open issues. If that can be useful to anyone in the future, yes it is possible: https://github.com/VinF/deer/blob/bbb78169711d2182da4c55bb173eb869f311ac75/deer/learning_algos/q_net_keras.py#L70 https://github.com/VinF/deer/blob/bbb78169711d2182da4c55bb173eb869f311ac75/deer/learning_algos/q_net_keras.py#L82