f6c7f0d36f5326074f6796386006609e65c1f63f,examples/run.py,,,#,11

Before Change

                    help="The name of the algorithm to run.")
parser.add_argument("--train-episodes", type=int, default=100,
                    help="Number of train episodes.")
parser.add_argument("--test-episodes", type=int, default=10,
                    help="Number of test episodes.")
parser.add_argument("--gamma", type=float, default=0.9, help="Discount factor")
parser.add_argument("--action-regression", action="store_true",
                    help="If true, a separate regressor for each action"
                         "is used.")

After Change

initial_states = np.zeros((289, 2))
cont = 0
for i in range(-8, 9):
    for j in range(-8, 9):
        initial_states[cont, :] = [0.125 * i, 0.375 * j]
        cont += 1
print(np.mean(alg.evaluate(initial_states)))

Instances