def test_random_choice_for_terminal_state(self):
policy = RandomPolicy()
policy.initialize_state(state='terminal', available_actions=set())
suggestion = policy.suggest_action_for_state('terminal')
self.assertIsNone(suggestion)
def test_random_recommendation_in_available_actions(self):
pol = RandomPolicy()
pol.initialize_state('s1', available_actions={'a1', 'a2', 'a3'})
a0 = pol.suggest_action_for_state('s1')
self.assertTrue(a0 in {'a1', 'a2', 'a3'})
def test_random_choice_called(self):
policy = RandomPolicy()
policy.initialize_state('s1', available_actions=['a1', 'a2', 'a3'])
mocked_random_choice = MagicMock(return_value='a2')
# If the state is not yet known, a random available action is returned.
with patch('random.choice', mocked_random_choice):
a0 = policy.suggest_action_for_state('s1')
# Result is determined by the mocked "random" choice
self.assertEqual('a2', a0)
# Arguments of the mocked "random" choice should be available actions
mocked_random_choice.assert_called_with(['a1', 'a2', 'a3'])
