12d56ada4c9cf1ecda2668c13b442ccf996d9e87,examples/tf/cluster_demo.py,,run_task,#Any#,18

Before Change

    run_experiment can easily execute variants of the experiment on different
    machines
    
    env = TfEnv(env_name="CartPole-v1")

    policy = CategoricalMLPPolicy(
        env_spec=env.spec,
        // The neural network policy should have two hidden layers,
        // each with 32 hidden units.
        hidden_sizes=(32, 32))

    baseline = LinearFeatureBaseline(env_spec=env.spec)

    algo = TRPO(
        env=env,
        policy=policy,
        baseline=baseline,
        batch_size=4000,
        max_path_length=100,
        n_itr=40,
        discount=0.99,
        step_size=v["step_size"],
        // Uncomment both lines (this and the plot parameter below) to enable
        // plotting
        plot=True,
    )
    algo.train()


for step_size in [0.01, 0.05, 0.1]:
    for seed in [1, 11, 21, 31, 41]:

After Change

    run_experiment can easily execute variants of the experiment on different
    machines
    
    with LocalRunner() as runner:
        env = TfEnv(env_name="CartPole-v1")

        policy = CategoricalMLPPolicy(
            env_spec=env.spec,
            // The neural network policy should have two hidden layers,
            // each with 32 hidden units.
            hidden_sizes=(32, 32))

        baseline = LinearFeatureBaseline(env_spec=env.spec)

        algo = TRPO(
            env=env,
            policy=policy,
            baseline=baseline,
            max_path_length=100,
            discount=0.99,
            step_size=v["step_size"],
        )

        runner.setup(algo=algo, env=env)

        runner.train(
            n_epochs=40,
            batch_size=4000,
            // Uncomment to enable plotting
            // plot=True
        )


for step_size in [0.01, 0.05, 0.1]:
    for seed in [1, 11, 21, 31, 41]:
        run_experiment(
            run_task,

Instances