.gitignore

 *pycache*
 *ppo_policy*
+
+torch_training/Nets/

torch_training/dueling_double_dqn.py

@@ -20,7 +20,7 @@ double_dqn = True  # If using double dqn algorithm
 input_channels = 5  # Number of Input channels
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
-device = torch.device("cpu")
+#device = torch.device("cpu")
 print(device)
 
 

torch_training/multi_agent_training.py

@@ -4,6 +4,11 @@ import random
 import sys
 from collections import deque
 
+# make sure the root path is in system path
+from pathlib import Path
+base_dir = Path(__file__).resolve().parent.parent
+sys.path.append(str(base_dir))
+
 import matplotlib.pyplot as plt
 import numpy as np
 import torch

torch_training/render_agent_behavior.py

@@ -87,7 +87,7 @@ action_size = 5
 
 # We set the number of episodes we would like to train on
 if 'n_trials' not in locals():
-    n_trials = 60000
+    n_trials = 6000
 max_steps = int(3 * (env.height + env.width))
 eps = 1.
 eps_end = 0.005

torch_training/training_navigation.py

@@ -3,6 +3,11 @@ import random
 import sys
 from collections import deque
 
+# make sure the root path is in system path
+from pathlib import Path
+base_dir = Path(__file__).resolve().parent.parent
+sys.path.append(str(base_dir))
+
 import matplotlib.pyplot as plt
 import numpy as np
 import torch