search

weidler / RLaSpa

Reinforcement Learning in Latent Space
MIT License
5 stars 1 forks source link

Being able to save and continue training a model #18

Closed HansBambel closed 5 years ago

HansBambel commented 5 years ago

Training takes a long time. If it crashes intermediately we should be able to continue where it crashed without restarting the whole training.

dannigt commented 5 years ago

@adrigrillo, when restoring training with DDQN, are the following variables enough?

adrigrillo commented 5 years ago

With the target model should be enough. However, you have to copy the target in the current model during the process of loading a pretained model.

With regards to the optimizer and the memory is not necessary, better not to save them.

On Wed, 9 Jan 2019, 16:52 dannigt <notifications@github.com wrote:

@adrigrillo https://github.com/adrigrillo, when restoring training with DDQN, are the following variables enough?

  • current_model
  • target_model
  • optimizer
  • memory Can I resume target_model to the same as current_model (from the latest check point)?

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/weidler/RLaSpa/issues/18#issuecomment-452745987, or mute the thread https://github.com/notifications/unsubscribe-auth/ARWvRtuJbev6vXINwfTvpow_aHv4Whbaks5vBhA9gaJpZM4Z1wjI .

dannigt commented 5 years ago

With the target model should be enough. However, you have to copy the target in the current model during the process of loading a pretained model. With regards to the optimizer and the memory is not necessary, better not to save them. … On Wed, 9 Jan 2019, 16:52 dannigt @.*** wrote: @adrigrillo https://github.com/adrigrillo, when restoring training with DDQN, are the following variables enough? - current_model - target_model - optimizer - memory Can I resume target_model to the same as current_model (from the latest check point)? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#18 (comment)>, or mute the thread https://github.com/notifications/unsubscribe-auth/ARWvRtuJbev6vXINwfTvpow_aHv4Whbaks5vBhA9gaJpZM4Z1wjI .

Alright, thx! I thought ADAM adjusts the learning rate depending on the current epoch/episode. Is it the case here?

dannigt commented 5 years ago

TODO's