# Runs on a g3.16xl node with 5 m5.24xl workers
# Takes roughly 10 minutes.
atari-impala:
    env:
        grid_search:
            - BreakoutNoFrameskip-v4
            - BeamRiderNoFrameskip-v4
            - QbertNoFrameskip-v4
            - SpaceInvadersNoFrameskip-v4
    run: IMPALA
    stop:
        timesteps_total: 3000000
    config:
        sample_batch_size: 50
        train_batch_size: 500
        num_workers: 128
        num_envs_per_worker: 5
        clip_rewards: True
        lr_schedule: [
            [0, 0.0005],
            [20000000, 0.000000000001],
        ]