ray/rllib/tuned_examples/ppo/cartpole-ppo-fake-gpus.yaml

cartpole-ppo-fake-gpus:
    env: CartPole-v0
    run: PPO
    stop:
        episode_reward_mean: 150
        training_iteration: 400
    config:
        # Works for both torch and tf.
        framework: tf
        gamma: 0.99
        lr: 0.0003
        num_workers: 1
        observation_filter: MeanStdFilter
        num_sgd_iter: 6
        vf_loss_coeff: 0.01

        # Double batch size (2 GPUs).
        train_batch_size: 8000

        model:
            # Test w/ LSTMs.
            use_lstm: true
            fcnet_hiddens: [32]
            fcnet_activation: linear
            vf_share_layers: true

        # Fake 2 GPUs.
        num_gpus: 2
        _fake_gpus: true