# @OldAPIStack
# Runs on a g3.16xl node with 5 m5.24xl workers
# Takes roughly 10 minutes.
atari-impala:
    env:
        grid_search:
            - ale_py:ALE/Breakout-v5
            - ale_py:ALE/BeamRider-v5
            - ale_py:ALE/Qbert-v5
            - ale_py:ALE/SpaceInvaders-v5
    run: IMPALA
    stop:
        timesteps_total: 3000000
    config:
        # Make analogous to old v4 + NoFrameskip.
        env_config:
            frameskip: 1
            full_action_space: false
            repeat_action_probability: 0.0
        rollout_fragment_length: 50
        train_batch_size: 500
        num_env_runners: 128
        num_envs_per_env_runner: 5
        clip_rewards: True
        lr_schedule: [
            [0, 0.0005],
            [20000000, 0.000000000001],
        ]