1) model = PPO(policy = "MlpPolicy", 
            env = env, 
            n_steps = 1024,
            batch_size = 64,
            n_epochs = 4,
            gamma = 0.999,
            gae_lambda = 0.98,
            ent_coef = 0.01,
            verbose=1)
model.learn(total_timesteps = 500000)
mean_reward=193.60 +/- 21.32519973099738

2) model = PPO(policy = "MlpPolicy", 
            env = env, 
            n_steps = 1024,
            batch_size = 64,
            n_epochs = 8,
            gamma = 0.999,
            gae_lambda = 0.98,
            ent_coef = 0.01,
            verbose=1)
model.learn(total_timesteps = 500000)
mean_reward=235.09 +/- 21.878789192117072

3) model = PPO(policy = "MlpPolicy", 
            env = env, 
            n_steps = 1024,
            batch_size = 64,
            n_epochs = 8,
            gamma = 0.999,
            gae_lambda = 0.98,
            ent_coef = 0.01,
            verbose=1)
model.learn(total_timesteps = 1000000)