Update app.py

app.py

@@ -35,7 +35,11 @@ def load_model(env_name):
     model = PPO.load(checkpoint, custom_objects=custom_objects)
 
     return model
+    
+st.subheader("In game theory and optimization Nash Equilibrium loss minimization starts playing randomly but then by understanding ratios of action success to action-reward with an action (observe, decide/predict, act and then observe outcome the Deep RL agents go from 50% efficiency to 98-99% efficiency based on quality of decision without making mistakes.")
 
+st.subheader("list of agent environments https://github.com/DLR-RM/rl-baselines3-zoo/blob/master/benchmark.md")
+st.subheader("https://huggingface.co/sb3")
 
 env_name = st.selectbox(
     "Select environment",
@@ -44,6 +48,14 @@ env_name = st.selectbox(
         "QbertNoFrameskip-v4",
         "SpaceInvadersNoFrameskip-v4",
         "PongNoFrameskip-v4",
+        "AsteroidsNoFrameskip-v4",
+        "BeamRiderNoFrameskip-v4",
+        "BreakoutNoFrameskip-v4	",
+        "EnduroNoFrameskip-v4",
+        "MsPacmanNoFrameskip-v4",
+        "RoadRunnerNoFrameskip-v4",
+        "Swimmer-v3",
+        "Walker2d-v3",
     ),
 )