1
0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 03:30:19 +01:00

Cleanup imports.

Till now, most of the modules were importing all of the module objects
(variables, classes, functions, other imports) into module namespace,
which potentially could (and was) cause of unintentional use of class or
methods, which was indirect imported.

With this patch, all the star imports were substituted with top-level
module, which provides desired class or function.

Besides, all imports where sorted (where possible) in a way pep8[1]
suggests - first are imports from standard library, than goes third
party imports (like numpy, tensorflow etc) and finally coach modules.
All of those sections are separated by one empty line.

[1] https://www.python.org/dev/peps/pep-0008/#imports
This commit is contained in:
Roman Dobosz
2018-04-12 19:46:32 +02:00
parent cafa152382
commit 1b095aeeca
75 changed files with 1169 additions and 1139 deletions

View File

@@ -13,19 +13,16 @@
# See the License for the specific language governing permissions and
# limitations under the License.
#
import numpy as np
from agents.value_optimization_agent import ValueOptimizationAgent
from agents import value_optimization_agent as voa
from logger import screen
from utils import RunPhase
import utils
# Neural Episodic Control - https://arxiv.org/pdf/1703.01988.pdf
class NECAgent(ValueOptimizationAgent):
class NECAgent(voa.ValueOptimizationAgent):
def __init__(self, env, tuning_parameters, replicated_device=None, thread_id=0):
ValueOptimizationAgent.__init__(self, env, tuning_parameters, replicated_device, thread_id,
create_target_network=False)
voa.ValueOptimizationAgent.__init__(self, env, tuning_parameters, replicated_device, thread_id,
create_target_network=False)
self.current_episode_state_embeddings = []
self.training_started = False
@@ -52,7 +49,7 @@ class NECAgent(ValueOptimizationAgent):
return total_loss
def act(self, phase=RunPhase.TRAIN):
def act(self, phase=utils.RunPhase.TRAIN):
if self.in_heatup:
# get embedding in heatup (otherwise we get it through choose_action)
embedding = self.main_network.online_network.predict(