Upload a2c_sb3_cartpole.py

a2c_sb3_cartpole.py

@@ -0,0 +1,15 @@
+import gym
+
+from stable_baselines3 import A2C
+
+env = gym.make("CartPole-v1")
+
+model = A2C("MlpPolicy", env, verbose=1)
+model.learn(total_timesteps=10000)
+
+vec_env = model.get_env()
+obs = vec_env.reset()
+for i in range(1000):
+    action, _state = model.predict(obs, deterministic=True)
+    obs, reward, done, info = vec_env.step(action)
+    vec_env.render()