Upload config.yaml

config.yaml

@@ -8,8 +8,8 @@ settings:
   frame_shape: !!python/tuple [128, 128, 1]
   continue_game: 0.0
   action_space: "discrete"
-  characters: "Ken"
-  difficulty: 6
+  characters: !!python/tuple ["Ken", "Ryu"]
+  difficulty: 7
   outfits: 2
 
 wrappers_settings:
@@ -31,7 +31,7 @@ policy_kwargs:
 
 ppo_settings:
   gamma: 0.94
-  model_checkpoint: "100000"     # 0: No checkpoint, 100000: Load checkpoint (if previously trained for 100000 steps)
+  model_checkpoint: "600000"     # 0: No checkpoint, else: Load checkpoint (if previously trained)
   learning_rate: [2.5e-4, 2.5e-6] # To start
   clip_range: [0.15, 0.025] # To start
   #learning_rate: [5.0e-5, 2.5e-6] # Fine Tuning
@@ -39,5 +39,5 @@ ppo_settings:
   batch_size: 512 #8 #nminibatches gave different batch size depending on the number of environments: batch_size = (n_steps * n_envs) // nminibatches
   n_epochs: 4
   n_steps: 512
-  autosave_freq: 10000
-  time_steps: 500000
+  autosave_freq: 50000
+  time_steps: 750000