基于keras的Actor Critic Method控制cart-pole

import gym
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

# Configuration paramaters for the whole setup
seed = 42
gamma = 0.99  # Discount factor for past rewards
max_steps_per_episode = 10000
env = gym.make("CartPole-v0")  # Create the environment
env.seed(seed)
eps = np.finfo(np.float32).eps.item()  # Smallest number such that 1.0 + eps != 1.0

num_inputs = 4
num_actions = 2
num_hidden = 128

inputs = layers.Input(shape=(num_inputs,))
common = layers.Dense(num_hidden, activation="relu")(inputs)
action = layers.Dense(num_actions, activation="softmax")(common)
critic = layers.Dense(1)(common)

model = keras.Model(inputs=inputs, outputs=[action, critic]<