ray/rllib/tuned_examples/ppo/cartpole-ppo-grid-search-example.yaml

cartpole-ppo-grid-search-example:
    env: CartPole-v0
    run: PPO
    stop:
        episode_reward_mean: 200
        time_total_s: 180
    config:
        # Works for both torch and tf.
        framework: tf
        num_workers: 2
        num_sgd_iter:
            grid_search: [1, 4]
        sgd_minibatch_size:
            grid_search: [128, 256, 512]