cartpole-sac:
    env: CartPole-v0
    run: SAC
    stop:
        episode_reward_mean: 100
        timesteps_total: 100000
    config:
        # Works for both torch and tf.
        framework: tf
        gamma: 0.95
        no_done_at_end: false
        target_network_update_freq: 32
        tau: 1.0
        # initial_alpha: 0.5
        train_batch_size: 32
        optimization:
            actor_learning_rate: 0.005
            critic_learning_rate: 0.005
            entropy_learning_rate: 0.0001
        # grad_norm_clipping: 40.0
        # evaluation_config:
        #     explore: true