d10e1736bef8954722d0d19631fe42f6b83e8ce6,examples/quickstart.py,,,#,24

Before Change

env = OpenAIGym("CartPole-v0")


config = Configuration(
    batch_size=4096,
    // Agent
    preprocessing=None,
    exploration=None,
    reward_preprocessing=None,
    // BatchAgent
    keep_last_timestep=True,
    // PPOAgent
    step_optimizer=dict(
        type="adam",
        learning_rate=1e-3
    ),
    optimization_steps=10,
    // Model
    scope="ppo",
    discount=0.99,
    // DistributionModel
    distributions=None,  // not documented!!!
    entropy_regularization=0.01,
    // PGModel
    baseline_mode=None,
    baseline=None,
    baseline_optimizer=None,
    gae_lambda=None,
    normalize_rewards=False,
    // PGLRModel
    likelihood_ratio_clipping=0.2,
    // Logging
    log_level="info",
    // TensorFlow Summaries
    summary_logdir=None,
    summary_labels=["total-loss"],
    summary_frequency=1,
    // Distributed
    // TensorFlow distributed configuration
    cluster_spec=None,
    parameter_server=False,
    task_index=0,
    device=None,
    local_model=False,
    replica_model=False,
)

// Network as list of layers
network_spec = [
    dict(type="dense", size=32, activation="tanh"),
    dict(type="dense", size=32, activation="tanh")
]

agent = PPOAgent(
    states_spec=env.states,
    actions_spec=env.actions,
    network_spec=network_spec,
    config=config
)

// Create the runner
runner = Runner(agent=agent, environment=env)

After Change

    dict(type="dense", size=32, activation="tanh")
]

agent = PPOAgent(
    states_spec=env.states,
    actions_spec=env.actions,
    network_spec=network_spec,
    batch_size=4096,
    // Agent
    preprocessing=None,
    exploration=None,
    reward_preprocessing=None,
    // BatchAgent
    keep_last_timestep=True,
    // PPOAgent
    step_optimizer=dict(
        type="adam",
        learning_rate=1e-3
    ),
    optimization_steps=10,
    // Model
    scope="ppo",
    discount=0.99,
    // DistributionModel
    distributions_spec=None,
    entropy_regularization=0.01,
    // PGModel
    baseline_mode=None,
    baseline=None,
    baseline_optimizer=None,
    gae_lambda=None,
    normalize_rewards=False,
    // PGLRModel
    likelihood_ratio_clipping=0.2,
    summary_spec=None,
    distributed_spec=None
)

// Create the runner
runner = Runner(agent=agent, environment=env)

Instances