# This can be expected to reach -160 reward within 2.5 timesteps / ~250 seconds on a K40 GPU
pendulum-apex-ddpg:
    env: Pendulum-v1
    run: APEX_DDPG
    stop:
        sampler_results/episode_reward_mean: -160
    config:
        # Works for both torch and tf.
        framework: torch
        use_huber: True
        clip_rewards: False
        num_workers: 16
        n_step: 1
        target_network_update_freq: 50000
        tau: 1.0
        evaluation_interval: 5
        evaluation_duration: 10