atari-impala:
    env:
        grid_search:
            - BreakoutNoFrameskip-v4
            - BeamRiderNoFrameskip-v4
            - PongNoFrameskip-v4
    run: IMPALA
    local_dir: ~/ray_results/
    stop:
        time_total_s: 3600
    config:
        sample_batch_size: 50
        train_batch_size: 500
        num_gpus: 0.5
        num_workers:
            grid_search: [4, 8, 16]
        num_envs_per_worker: 5
        clip_rewards: True
        lr_schedule: [
            [0, 0.0005],
            [20000000, 0.000000000001],
        ]

atari-impala:
    env:
        grid_search:
            - BreakoutNoFrameskip-v4
            - BeamRiderNoFrameskip-v4
            - PongNoFrameskip-v4
    run: IMPALA
    local_dir: ~/ray_results/
    stop:
        time_total_s: 3600
    config:
        sample_batch_size: 50
        train_batch_size: 500
        num_gpus: 1
        num_workers:
            grid_search: [4, 8, 16, 32]
        num_envs_per_worker: 5
        clip_rewards: True
        lr_schedule: [
            [0, 0.0005],
            [20000000, 0.000000000001],
        ]

atari-impala:
    env:
        grid_search:
            - BreakoutNoFrameskip-v4
            - BeamRiderNoFrameskip-v4
            - PongNoFrameskip-v4
    run: IMPALA
    local_dir: ~/ray_results/
    stop:
        time_total_s: 3600
    config:
        sample_batch_size: 50
        train_batch_size: 500
        num_gpus: 2
        num_workers:
            grid_search: [4, 8, 16, 32, 64]
        num_envs_per_worker: 5
        clip_rewards: True
        lr_schedule: [
            [0, 0.0005],
            [20000000, 0.000000000001],
        ]