Fix Train Agent doc, need env param (#1239)

satur9nine · web-flow · commit 057bfef49ef4 · 2024-11-04T10:06:04.000Z
diff --git a/docs/introduction/train_agent.md b/docs/introduction/train_agent.md
@@ -116,6 +116,7 @@ epsilon_decay = start_epsilon / (n_episodes / 2)  # reduce the exploration over
 final_epsilon = 0.1
 
 agent = BlackjackAgent(
+    env,
     learning_rate=learning_rate,
     initial_epsilon=start_epsilon,
     epsilon_decay=epsilon_decay,
