cartpole-a2c-microbatch:
    env: CartPole-v0
    run: A2C
    stop:
        episode_reward_mean: 150
        timesteps_total: 100000
    config:
        # Works for both torch and tf.
        framework: tf
        num_workers: 1
        gamma: 0.95
        microbatch_size: 50
        train_batch_size: 100