reinforce-learningrate #actions1,2,3,4

actions.py

@@ -1,14 +1,14 @@
 available_actions = [
-    [0.0, 0.7, 0.0],  # throttle
-    [0.0, 0.5, 0.0],  # throttle
-    [0.0, 0.2, 0.0],  # throttle
+    [0.0, 0.25, 0.0],  # throttle
+    [0.0, 0.1, 0.0],  # throttle
+    [0.0, 0.0, 0.0],  # throttle
     [0.0, 0.0, 0.7],  # break
     [0.0, 0.0, 0.5],  # break
     [0.0, 0.0, 0.2],  # break
-    [-0.8, 0.1, 0.0],  # left
-    [-0.5, 0.1, 0.0],  # left
-    [-0.2, 0.1, 0.0],  # left
-    [0.8, 0.1, 0.0],  # right
-    [0.5, 0.1, 0.0],  # right
-    [0.2, 0.1, 0.0],  # right
+    [-1.0, 0.0, 0.04],  # left
+    [-0.5, 0.0, 0.04],  # left
+    [-0.2, 0.0, 0.04],  # left
+    [1.0, 0.0, 0.04],  # right
+    [0.5, 0.0, 0.04],  # right
+    [0.2, 0.0, 0.04],  # right
 ]

main.py

@@ -12,7 +12,7 @@
 
 if __name__ == "__main__":
     hyperparams = {
-        'num_episodes': 40000,  # Number of training episodes
+        'num_episodes': 150000,  # Number of training episodes
         'lr': 1e-3,  # Learning rate
         'gamma': 0.99,  # Discount rate
         'log_interval': 10,  # controls how often we log progress