本文整理汇总了Python中pybullet_utils.logger.Logger.dump_tabular方法的典型用法代码示例。如果您正苦于以下问题：Python Logger.dump_tabular方法的具体用法？Python Logger.dump_tabular怎么用？Python Logger.dump_tabular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pybullet_utils.logger.Logger的用法示例。
在下文中一共展示了Logger.dump_tabular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: Logger
# 需要导入模块: from pybullet_utils.logger import Logger [as 别名]
# 或者: from pybullet_utils.logger.Logger import dump_tabular [as 别名]
from pybullet_utils.logger import Logger
logger = Logger()
logger.configure_output_file("e:/mylog.txt")
for i in range (10):
logger.log_tabular("Iteration", 1)
Logger.print2("hello world")
logger.print_tabular()
logger.dump_tabular()示例2: RLAgent
# 需要导入模块: from pybullet_utils.logger import Logger [as 别名]
# 或者: from pybullet_utils.logger.Logger import dump_tabular [as 别名]
#.........这里部分代码省略.........
self.train_return = path.calc_return()
if self._need_normalizer_update:
self._record_normalizers(path)
return path_id
def _record_normalizers(self, path):
states = np.array(path.states)
self.s_norm.record(states)
if self.has_goal():
goals = np.array(path.goals)
self.g_norm.record(goals)
return
def _update_normalizers(self):
self.s_norm.update()
if self.has_goal():
self.g_norm.update()
return
def _train(self):
samples = self.replay_buffer.total_count
self._total_sample_count = int(MPIUtil.reduce_sum(samples))
end_training = False
if (self.replay_buffer_initialized):
if (self._valid_train_step()):
prev_iter = self.iter
iters = self._get_iters_per_update()
avg_train_return = MPIUtil.reduce_avg(self.train_return)
for i in range(iters):
curr_iter = self.iter
wall_time = time.time() - self.start_time
wall_time /= 60 * 60 # store time in hours
has_goal = self.has_goal()
s_mean = np.mean(self.s_norm.mean)
s_std = np.mean(self.s_norm.std)
g_mean = np.mean(self.g_norm.mean) if has_goal else 0
g_std = np.mean(self.g_norm.std) if has_goal else 0
self.logger.log_tabular("Iteration", self.iter)
self.logger.log_tabular("Wall_Time", wall_time)
self.logger.log_tabular("Samples", self._total_sample_count)
self.logger.log_tabular("Train_Return", avg_train_return)
self.logger.log_tabular("Test_Return", self.avg_test_return)
self.logger.log_tabular("State_Mean", s_mean)
self.logger.log_tabular("State_Std", s_std)
self.logger.log_tabular("Goal_Mean", g_mean)
self.logger.log_tabular("Goal_Std", g_std)
self._log_exp_params()
self._update_iter(self.iter + 1)
self._train_step()
Logger.print2("Agent " + str(self.id))
self.logger.print_tabular()
Logger.print2("")
if (self._enable_output() and curr_iter % self.int_output_iters == 0):
self.logger.dump_tabular()
if (prev_iter // self.int_output_iters != self.iter // self.int_output_iters):
end_training = self.enable_testing()
else:
Logger.print2("Agent " + str(self.id))
Logger.print2("Samples: " + str(self._total_sample_count))
Logger.print2("")
if (self._total_sample_count >= self.init_samples):
self.replay_buffer_initialized = True
end_training = self.enable_testing()
if self._need_normalizer_update:
self._update_normalizers()
self._need_normalizer_update = self.normalizer_samples > self._total_sample_count
if end_training:
self._init_mode_train_end()
return
def _get_iters_per_update(self):
return MPIUtil.get_num_procs() * self.iters_per_update
def _valid_train_step(self):
return True
def _log_exp_params(self):
self.logger.log_tabular("Exp_Rate", self.exp_params_curr.rate)
self.logger.log_tabular("Exp_Noise", self.exp_params_curr.noise)
self.logger.log_tabular("Exp_Temp", self.exp_params_curr.temp)
return