Skip to content

Remove env creation logic from TrainerController #1562

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Jan 24, 2019
Merged

Remove env creation logic from TrainerController #1562

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e8db306
Remove env creation logic from TrainerController
harper-u3d Dec 6, 2018
8d3e10c
Tweaks based on PR feedback
harper-u3d Jan 4, 2019
45b083b
Adds back train_mode parameter to UnityEnvironment
harper-u3d Jan 23, 2019
9a323f5
Final tweaks to fix merge issues
harper-u3d Jan 24, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Final tweaks to fix merge issues
  • Loading branch information
@harper-u3d
harper-u3d committed Jan 24, 2019
commit 9a323f5cf6bd39052e00f91b3ff42c502816b2a8
5 changes: 2 additions & 3 deletions ml-agents/mlagents/trainers/trainer_controller.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -196,8 +196,7 @@ def start_learning(self, env, trainer_config):
for _, t in self.trainers.items():
self.logger.info(t)

global_step = 0 # This is only for saving the model
curr_info = self._reset_env()
curr_info = self._reset_env(env)
if self.train_model:
for brain_name, trainer in self.trainers.items():
trainer.write_tensorboard_text('Hyperparameters',
Expand All @@ -211,7 +210,7 @@ def start_learning(self, env, trainer_config):
or not self.train_model:
new_info = self.take_step(env, curr_info)
self.global_step += 1
if global_step % self.save_freq == 0 and self.global_step != 0 \
if self.global_step % self.save_freq == 0 and self.global_step != 0 \
and self.train_model:
# Save Tensorflow model
self._save_model(steps=self.global_step)
Expand Down
6 changes: 3 additions & 3 deletions ml-agents/tests/trainers/test_trainer_controller.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -279,7 +279,7 @@ def trainer_controller_with_start_learning_mocks():
tc.trainers = {'testbrain': trainer_mock}
tc.take_step = MagicMock()

def take_step_sideeffect(env, curr_info, global_step):
def take_step_sideeffect(env, curr_info):
tc.trainers['testbrain'].get_step += 1
if tc.trainers['testbrain'].get_step > 10:
raise KeyboardInterrupt
Expand Down Expand Up @@ -382,7 +382,7 @@ def test_take_step_resets_env_on_global_done():
env_mock.reset = MagicMock(return_value=brain_info_mock)
env_mock.global_done = True

tc.take_step(env_mock, brain_info_mock, 0)
tc.take_step(env_mock, brain_info_mock)
env_mock.reset.assert_called_once()


Expand All @@ -407,7 +407,7 @@ def test_take_step_adds_experiences_to_trainer_and_trains():
env_mock.reset = MagicMock(return_value=curr_info_mock)
env_mock.global_done = False

tc.take_step(env_mock, curr_info_mock, 0)
tc.take_step(env_mock, curr_info_mock)
env_mock.reset.assert_not_called()
trainer_mock.take_action.assert_called_once_with(curr_info_mock)
env_mock.step.assert_called_once_with(
Expand Down