# Runs on a single g3.16xl node
# See https://github.com/ray-project/rl-experiments for results
atari-ppo:
    env:
        grid_search:
            - BreakoutNoFrameskip-v4
            - BeamRiderNoFrameskip-v4
            - QbertNoFrameskip-v4
            - SpaceInvadersNoFrameskip-v4
    run: PPO
    config:
        # Works for both torch and tf.
        framework: tf
        lambda: 0.95
        kl_coeff: 0.5
        clip_rewards: True
        clip_param: 0.1
        vf_clip_param: 10.0
        entropy_coeff: 0.01
        train_batch_size: 5000
        rollout_fragment_length: 100
        sgd_minibatch_size: 500
        num_sgd_iter: 10
        num_workers: 10
        num_envs_per_worker: 5
        batch_mode: truncate_episodes
        observation_filter: NoFilter
        model:
            vf_share_layers: true
        num_gpus: 1