# Runs on a single g3.4xl node
# See https://github.com/ray-project/rl-experiments for results
atari-basic-dqn:
    env:
        grid_search:
            - BreakoutNoFrameskip-v4
            - BeamRiderNoFrameskip-v4
            - QbertNoFrameskip-v4
            - SpaceInvadersNoFrameskip-v4
    run: DQN
    config:
        double_q: false
        dueling: false
        num_atoms: 1
        noisy: false
        prioritized_replay: false
        n_step: 1
        target_network_update_freq: 8000
        lr: .0000625
        adam_epsilon: .00015
        hiddens: [512]
        learning_starts: 20000
        buffer_size: 1000000
        sample_batch_size: 4
        train_batch_size: 32
        schedule_max_timesteps: 2000000
        exploration_final_eps: 0.01
        exploration_fraction: .1
        prioritized_replay_alpha: 0.5
        beta_annealing_fraction: 1.0
        final_prioritized_replay_beta: 1.0
        num_gpus: 0.2
        timesteps_per_iteration: 10000