ddpg_nets_dm.py 文件源码

def qfunction(obs, act, theta, name="qfunction"):
    with tf.variable_op_scope([obs, act], name, name):
        h0 = tf.identity(obs, name='h0-obs')
        h0a = tf.identity(act, name='h0-act')
        h1 = tf.nn.relu(tf.matmul(h0, theta[0]) + theta[1], name='h1')
        h1a = tf.concat(1, [h1, act])
        h2 = tf.nn.relu(tf.matmul(h1a, theta[2]) + theta[3], name='h2')
        qs = tf.matmul(h2, theta[4]) + theta[5]
        q = tf.squeeze(qs, [1], name='h3-q')
        return q