本文整理匯總了Python中objective.PCL屬性的典型用法代碼示例。如果您正苦於以下問題：Python objective.PCL屬性的具體用法？Python objective.PCL怎麽用？Python objective.PCL使用的例子？那麽, 這裏精選的屬性代碼示例或許可以為您提供幫助。您也可以進一步了解該屬性所在類objective的用法示例。
在下文中一共展示了objective.PCL屬性的2個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: get_objective
# 需要導入模塊: import objective [as 別名]
# 或者: from objective import PCL [as 別名]
def get_objective(self):
tau = self.tau
if self.tau_decay is not None:
assert self.tau_start >= self.tau
tau = tf.maximum(
tf.train.exponential_decay(
self.tau_start, self.global_step, 100, self.tau_decay),
self.tau)
if self.objective in ['pcl', 'a3c', 'trpo', 'upcl']:
cls = (objective.PCL if self.objective in ['pcl', 'upcl'] else
objective.TRPO if self.objective == 'trpo' else
objective.ActorCritic)
policy_weight = 1.0
return cls(self.learning_rate,
clip_norm=self.clip_norm,
policy_weight=policy_weight,
critic_weight=self.critic_weight,
tau=tau, gamma=self.gamma, rollout=self.rollout,
eps_lambda=self.eps_lambda, clip_adv=self.clip_adv)
elif self.objective in ['reinforce', 'urex']:
cls = (full_episode_objective.Reinforce
if self.objective == 'reinforce' else
full_episode_objective.UREX)
return cls(self.learning_rate,
clip_norm=self.clip_norm,
num_samples=self.num_samples,
tau=tau, bonus_weight=1.0) # TODO: bonus weight?
else:
assert False, 'Unknown objective %s' % self.objective 示例2: get_objective
# 需要導入模塊: import objective [as 別名]
# 或者: from objective import PCL [as 別名]
def get_objective(self):
tau = self.tau
if self.tau_decay is not None:
assert self.tau_start >= self.tau
tau = tf.maximum(
tf.train.exponential_decay(
self.tau_start, self.global_step, 100, self.tau_decay),
self.tau)
if self.objective in ['pcl', 'a3c', 'trpo', 'upcl']:
cls = (objective.PCL if self.objective in ['pcl', 'upcl'] else
objective.TRPO if self.objective == 'trpo' else
objective.ActorCritic)
policy_weight = 1.0
return cls(self.learning_rate,
clip_norm=self.clip_norm,
policy_weight=policy_weight,
critic_weight=self.critic_weight,
tau=tau, gamma=self.gamma, rollout=self.rollout,
eps_lambda=self.eps_lambda, clip_adv=self.clip_adv,
use_target_values=self.use_target_values)
elif self.objective in ['reinforce', 'urex']:
cls = (full_episode_objective.Reinforce
if self.objective == 'reinforce' else
full_episode_objective.UREX)
return cls(self.learning_rate,
clip_norm=self.clip_norm,
num_samples=self.num_samples,
tau=tau, bonus_weight=1.0) # TODO: bonus weight?
else:
assert False, 'Unknown objective %s' % self.objective