def __init__(self, scope):
with tf.variable_scope("%s_shared" % scope):
self.obs = obs = tf.placeholder(
tf.float32, shape=[None, pms.obs_shape], name="%s_obs"%scope)
self.action_n = tf.placeholder(tf.float32, shape=[None, pms.action_shape], name="%s_action"%scope)
self.advant = tf.placeholder(tf.float32, shape=[None], name="%s_advant"%scope)
self.old_dist_means_n = tf.placeholder(tf.float32, shape=[None, pms.action_shape],
name="%s_oldaction_dist_means"%scope)
self.old_dist_logstds_n = tf.placeholder(tf.float32, shape=[None, pms.action_shape],
name="%s_oldaction_dist_logstds"%scope)
self.action_dist_means_n = (pt.wrap(self.obs).
fully_connected(64, activation_fn=tf.nn.relu, init=tf.random_normal_initializer(-0.05, 0.05), bias_init=tf.constant_initializer(0),
name="%s_fc1"%scope).
fully_connected(64, activation_fn=tf.nn.relu, init=tf.random_normal_initializer(-0.05, 0.05), bias_init=tf.constant_initializer(0),
name="%s_fc2"%scope).
fully_connected(pms.action_shape, init=tf.random_normal_initializer(-0.05, 0.05), bias_init=tf.constant_initializer(0),
name="%s_fc3"%scope))
self.N = tf.shape(obs)[0]
Nf = tf.cast(self.N, tf.float32)
self.action_dist_logstd_param = tf.Variable((.01*np.random.randn(1, pms.action_shape)).astype(np.float32), name="%spolicy_logstd"%scope)
self.action_dist_logstds_n = tf.tile(self.action_dist_logstd_param,
tf.pack((tf.shape(self.action_dist_means_n)[0], 1)))
self.var_list = [v for v in tf.trainable_variables()if v.name.startswith(scope)]
评论列表
文章目录
