# Runs on a single g3.16xl AWS machine
apex:
    env:
        grid_search:
            - BreakoutNoFrameskip-v4
            - BeamRiderNoFrameskip-v4
            - QbertNoFrameskip-v4
            - SpaceInvadersNoFrameskip-v4
    run: APEX
    config:
        # Works for both torch and tf.
        framework: tf
        double_q: false
        dueling: false
        num_atoms: 1
        noisy: false
        n_step: 3
        lr: .0001
        adam_epsilon: .00015
        hiddens: [512]
        buffer_size: 1000000
        prioritized_replay_alpha: 0.5
        final_prioritized_replay_beta: 1.0
        prioritized_replay_beta_annealing_timesteps: 2000000

        num_gpus: 1

        # APEX
        num_workers: 8
        num_envs_per_worker: 8
        rollout_fragment_length: 20
        train_batch_size: 512
        target_network_update_freq: 50000
        timesteps_per_iteration: 25000