tatk.policy.mle package¶
Subpackages¶
Submodules¶
tatk.policy.mle.loader module¶
tatk.policy.mle.mle module¶
-
class
tatk.policy.mle.mle.
MLEAbstract
(archive_file, model_file)¶ Bases:
tatk.policy.policy.Policy
-
__init__
(archive_file, model_file)¶ Initialize self. See help(type(self)) for accurate signature.
-
init_session
()¶ Restore after one session
-
load
(archive_file, model_file, filename)¶
-
predict
(state)¶ Predict an system action given state. Args:
state (dict): Dialog state. Please refer to util/state.py
- Returns:
action : System act, with the form of (act_type, {slot_name_1: value_1, slot_name_2, value_2, …})
-
tatk.policy.mle.train module¶
-
class
tatk.policy.mle.train.
MLE_Trainer_Abstract
(manager, cfg)¶ Bases:
object
-
__init__
(manager, cfg)¶ Initialize self. See help(type(self)) for accurate signature.
-
imit_test
(epoch, best)¶ provide an unbiased evaluation of the policy fit on the training dataset
-
imitating
(epoch)¶ pretrain the policy by simple imitation learning (behavioral cloning)
-
policy_loop
(data)¶
-
save
(directory, epoch)¶
-
test
()¶
-