Update app.py

app.py

@@ -42,6 +42,11 @@ def replay(model_id, filename, environment, evaluate):
 		obs, rewards, dones, info = env.step(action)
 	# Save the video
 	env.close()
+	
+	mean_reward, std_reward = evaluate_policy(model, env, n_eval_episodes=10)
+	print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
+	
+	return f"mean_reward={mean_reward:.2f} +/- {std_reward}", "video"
 
 
 iface = gr.Interface(fn=replay, inputs=[
@@ -52,5 +57,5 @@ iface = gr.Interface(fn=replay, inputs=[
                                         ]
 
 
-, outputs="video")
+, outputs=["text", "video"])
 iface.launch()