More logging and checkpoints for training

NaXzyu · Apr 9, 2024 · 2e4c128 · 2e4c128
1 parent fd896f1
commit 2e4c128
Showing 1 changed file with 4 additions and 4 deletions.
diff --git a/config/Dialogos-a0a.sac.yaml b/config/Dialogos-a0a.sac.yaml
@@ -1,5 +1,5 @@
 behaviors:
-  Kyle:
+  Dialogos:
     trainer_type: sac
     hyperparameters:
       learning_rate: 0.0003
@@ -28,8 +28,8 @@ behaviors:
         network_settings:
           hidden_units: 256
           learning_rate: 0.0001
-    keep_checkpoints: 40
-    checkpoint_interval: 500000
-    max_steps: 20000000
+    keep_checkpoints: 100
+    checkpoint_interval: 10000
+    max_steps: 1000000
     time_horizon: 1000
     summary_freq: 10000