model = PPO(
  policy = 'MlpPolicy',
  env = env,
  n_steps = 2048,
  batch_size = 512,
  n_epochs = 4,
  gamma = 0.099,
  gae_lambda = 0.98,
  ent_coef = 0.01,
  learning_rate=0.00001,
  verbose=1,
  tensorboard_log="./ppo_tensorboard/")
  
model.learn(total_timesteps=int(10e6))