gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 03:30:19 +01:00
Code Issues Projects Releases Wiki Activity

network_imporvements branch merge

Browse Source
This commit is contained in:
Shadi Endrawis
2018-10-02 13:41:46 +03:00
parent 72ea933384
commit 51726a5b80
110 changed files with 1639 additions and 1161 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
rl_coach/agents/ddpg_agent.py
View File

@@ -41,8 +41,6 @@ class DDPGCriticNetworkParameters(NetworkParameters):
'action': InputEmbedderParameters(scheme=EmbedderScheme.Shallow)}
self.middleware_parameters = FCMiddlewareParameters()
self.heads_parameters = [VHeadParameters()]
self.loss_weights = [1.0]
self.rescale_gradient_from_head_by_factor = [1]
self.optimizer_type = 'Adam'
self.batch_size = 64
self.async_training = False
@@ -58,8 +56,6 @@ class DDPGActorNetworkParameters(NetworkParameters):
self.input_embedders_parameters = {'observation': InputEmbedderParameters(batchnorm=True)}
self.middleware_parameters = FCMiddlewareParameters(batchnorm=True)
self.heads_parameters = [DDPGActorHeadParameters()]
self.loss_weights = [1.0]
self.rescale_gradient_from_head_by_factor = [1]
self.optimizer_type = 'Adam'
self.batch_size = 64
self.async_training = False