def objective(self, trial, n_episodes=100):
        lr = trial.suggest_loguniform('lr', 1e-5, 1e-1)
        gamma = trial.suggest_uniform('gamma', 0.9, 0.999)
        optimizer = optim.Adam(self.policy_network.parameters(), lr=lr)
        trainer = REINFORCE(self.env, self.policy_network, optimizer, self.model_path, gamma=gamma)
        reward = trainer.train(n_episodes, save_model=False, save_video=False)
        return reward