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

Before Change

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

A_BOUND = [env.action_space.low, env.action_space.high]
A_BOUND[0] = A_BOUND[0].reshape(1, N_A)
A_BOUND[1] = A_BOUND[1].reshape(1, N_A)
// print(A_BOUND)

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  ////////////////////////////////////////

GAME = "BipedalWalker-v2"  // BipedalWalkerHardcore-v2   BipedalWalker-v2  LunarLanderContinuous-v2

Instances