# Taken from rllib/tuned_examples/atari_impala_large.yaml
# Runs on a g3.16xl node with 5 m5.24xlarge workers
# Should take roughly 100 minutes.
atari-impala:
    env:
        grid_search:
            - BreakoutNoFrameskip-v4
            - BeamRiderNoFrameskip-v4
            - QbertNoFrameskip-v4
            - SpaceInvadersNoFrameskip-v4
    run: IMPALA
    # Minimum reward and total ts (in given time_total_s) to pass this test.
    pass_criteria:
        timesteps_total: 45000000
    stop:
        time_total_s: 3600
    frameworks: [ "tf" ]
    config:
        num_gpus: 1
        num_cpus_for_driver: 0
        rollout_fragment_length: 50
        train_batch_size: 500
        num_workers: 128
        num_envs_per_worker: 5
        clip_rewards: True
        lr_schedule: [
            [0, 0.0005],
            [20000000, 0.000000000001],
        ]