go

agent.py

@@ -31,7 +31,7 @@ class RandomAgent():
 
 class qLearningAgent:
     def __init__(self, mat, TD_lambda = 0.8, alpha = 0.005, gamma = 0.8, epsilon = 0.01):
-        self.state_per_tile = 10
+        self.state_per_tile = 11
         self.alpha = alpha
         self.gamma = gamma
         self.epsilon = epsilon # e-greedy