Update app.py

app.py

@@ -52,13 +52,13 @@ st.markdown(
     'Simulate A/B optimization with policy gradient reinforcement learning')
 
 
-lr = float(st.text_input('Learning rate', value=0.1))
+lr = float(st.text_input('Learning rate', value=0.5))
 
-prob_A = float(st.text_input('Click probability of ad A', value=0.4))
+prob_A = float(st.text_input('Click probability of ad A', value=0.3))
 
-prob_B = float(st.text_input('Click probability of ad B', value=0.5))
+prob_B = float(st.text_input('Click probability of ad B', value=0.54
 
-epochs = int(st.text_input('Number of ad impressions (epochs)', value=2000))
+epochs = int(st.text_input('Number of ad impressions (epochs)', value=1000))
 
 information_for_plotting = np.zeros((epochs, 10))