Rename greedy_policy to epsilon_greedy_policy

izmendi · Mar 18, 2015 · baf9901 · baf9901
1 parent 211f3ec
commit baf9901
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/mc_control.py b/mc_control.py
@@ -6,7 +6,7 @@
 
 # if our random value > epsilon, then pick HIT or STICK, depending on which action is better (exploitation)
 # else randomly return HIT or STICK (exploration)
-def greedy_policy(action_value, state, epsilon):
+def epsilon_greedy_policy(action_value, state, epsilon):
     HIT, STICK = 1, 0
     if random() > epsilon:
         hit_value = action_value[(state.dealer, state.player, HIT)]
@@ -69,7 +69,7 @@ def plot_value_function(value_function, title):
             dealer = state.dealer
 
             epsilon = float(n_zero) / (n_zero + n_states[(dealer, player)])
-            action = greedy_policy(action_value_function, state, epsilon)
+            action = epsilon_greedy_policy(action_value_function, state, epsilon)
 
             n_states[(dealer, player)] += 1
             n_state_actions[(dealer, player, action)] += 1