本文整理汇总了Python中objective.ActorCritic方法的典型用法代码示例。如果您正苦于以下问题：Python objective.ActorCritic方法的具体用法？Python objective.ActorCritic怎么用？Python objective.ActorCritic使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类objective的用法示例。
在下文中一共展示了objective.ActorCritic方法的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: get_objective
# 需要导入模块: import objective [as 别名]
# 或者: from objective import ActorCritic [as 别名]
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
# 需要导入模块: import objective [as 别名]
# 或者: from objective import ActorCritic [as 别名]
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