a0d0c18fcde09f06be9ca1556052cf8064df4ac6,examples/reinforcement_learning/tutorial_A3C.py,,,#,52

Before Change

GLOBAL_RUNNING_R = []
GLOBAL_EP = 0  // will increase during training, stop training when it >= MAX_GLOBAL_EP

env = gym.make(GAME)

N_S = env.observation_space.shape[0]
N_A = env.action_space.shape[0]

After Change

tf.random.set_seed(2)  // reproducible

// add arguments in command  --train/test
parser = argparse.ArgumentParser(description="Train or test neural net motor controller.")
parser.add_argument("--train", dest="train", action="store_true", default=False)
parser.add_argument("--test", dest="test", action="store_true", default=True)
args = parser.parse_args()

//////////////////////////////////////////  hyper parameters  ////////////////////////////////////////

Instances