def test_step_takes_steps_for_all_non_waiting_envs(self):
SubprocessEnvManager.create_worker = lambda em, worker_id, step_queue, env_factory, engine_c: MockEnvWorker(
worker_id, EnvironmentResponse("step", worker_id, worker_id))
manager = SubprocessEnvManager(mock_env_factory,
EngineConfig.default_config(), 3)
manager.step_queue = Mock()
manager.step_queue.get_nowait.side_effect = [
EnvironmentResponse("step", 0, StepResponse(0, None)),
EnvironmentResponse("step", 1, StepResponse(1, None)),
EmptyQueue(),
]
step_mock = Mock()
last_steps = [Mock(), Mock(), Mock()]
manager.env_workers[0].previous_step = last_steps[0]
manager.env_workers[1].previous_step = last_steps[1]
manager.env_workers[2].previous_step = last_steps[2]
manager.env_workers[2].waiting = True
manager._take_step = Mock(return_value=step_mock)
res = manager.step()
for i, env in enumerate(manager.env_workers):
if i < 2:
env.send.assert_called_with("step", step_mock)
manager.step_queue.get_nowait.assert_called()
# Check that the "last steps" are set to the value returned for each step
self.assertEqual(
manager.env_workers[i].previous_step.
current_all_brain_info, i)
assert res == [
manager.env_workers[0].previous_step,
manager.env_workers[1].previous_step,
]
def test_step_takes_steps_for_all_non_waiting_envs(self,
mock_create_worker):
mock_create_worker.side_effect = create_worker_mock
manager = SubprocessEnvManager(mock_env_factory,
EngineConfig.default_config(), 3)
manager.step_queue = Mock()
manager.step_queue.get_nowait.side_effect = [
EnvironmentResponse(EnvironmentCommand.STEP, 0,
StepResponse(0, None, {})),
EnvironmentResponse(EnvironmentCommand.STEP, 1,
StepResponse(1, None, {})),
EmptyQueue(),
]
step_mock = Mock()
last_steps = [Mock(), Mock(), Mock()]
manager.env_workers[0].previous_step = last_steps[0]
manager.env_workers[1].previous_step = last_steps[1]
manager.env_workers[2].previous_step = last_steps[2]
manager.env_workers[2].waiting = True
manager._take_step = Mock(return_value=step_mock)
res = manager._step()
for i, env in enumerate(manager.env_workers):
if i < 2:
env.send.assert_called_with(EnvironmentCommand.STEP, step_mock)
manager.step_queue.get_nowait.assert_called()
# Check that the "last steps" are set to the value returned for each step
self.assertEqual(
manager.env_workers[i].previous_step.
current_all_step_result, i)
assert res == [
manager.env_workers[0].previous_step,
manager.env_workers[1].previous_step,
]