7c6e84bbf65bcbade78e78d6120ca0997dff7c28,examples/pendulum_sac.py,,experiment,#Any#Any#Any#Any#,67

Before Change

        dataset = core.evaluate(n_steps=n_steps_test, render=False)
        J = compute_J(dataset, gamma)
        s, *_ = parse_dataset(dataset)
        print("J:", np.mean(J), "E:", agent.policy.entropy(s))

    print("Press a button to visualize pendulum")
    input()

After Change

def experiment(alg, n_epochs, n_steps, n_steps_test):
    np.random.seed()

    logger = Logger(alg.__name__, results_dir=None)
    logger.strong_line()
    logger.info("Experiment Algorithm: " + alg.__name__)

    // MDP
    horizon = 200
    gamma = 0.99

Instances