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

5
rl_coach/agents/policy_optimization_agent.py
View File

@@ -93,6 +93,8 @@ class PolicyOptimizationAgent(Agent):
total_loss = 0
if num_steps_passed_since_last_update > 0:
for network in self.networks.values():
network.set_is_training(True)
# we need to update the returns of the episode until now
episode.update_returns()
@@ -124,6 +126,9 @@ class PolicyOptimizationAgent(Agent):
network.apply_gradients_and_sync_networks()
self.training_iteration += 1
for network in self.networks.values():
network.set_is_training(False)
# run additional commands after the training is done
self.post_training_commands()