def test_take_action_returns_nones_on_missing_values():
test_seed = 3
policy = TFPolicy(test_seed, basic_mock_brain(), basic_params())
policy.evaluate = MagicMock(return_value={})
brain_info_with_agents = BrainInfo([], [], [], agents=["an-agent-id"])
result = policy.get_action(brain_info_with_agents)
assert result == ActionInfo(None, None, None, None, {})
def get_action(self, brain_info: BrainInfo) -> ActionInfo:
"""
Decides actions given observations information, and takes them in environment.
:param brain_info: A dictionary of brain names and BrainInfo from environment.
:return: an ActionInfo containing action, memories, values and an object
to be passed to add experiences
"""
if len(brain_info.agents) == 0:
return ActionInfo([], [], [], None, None)
run_out = self.evaluate(brain_info)
return ActionInfo(
action=run_out.get("action"),
memory=run_out.get("memory_out"),
text=None,
value=run_out.get("value"),
outputs=run_out,
)
def get_action(self, brain_info: BrainInfo) -> ActionInfo:
"""
Decides actions given observations information, and takes them in environment.
:param brain_info: A dictionary of brain names and BrainInfo from environment.
:return: an ActionInfo containing action, memories, values and an object
to be passed to add experiences
"""
if len(brain_info.agents) == 0:
return ActionInfo([], [], None)
agents_done = [
agent
for agent, done in zip(brain_info.agents, brain_info.local_done)
if done
]
self.remove_memories(agents_done)
self.remove_previous_action(agents_done)
run_out = self.evaluate(brain_info) # pylint: disable=assignment-from-no-return
self.save_memories(brain_info.agents, run_out.get("memory_out"))
return ActionInfo(action=run_out.get("action"),
value=run_out.get("value"),
outputs=run_out)
def test_take_action_returns_action_info_when_available():
test_seed = 3
policy = TFPolicy(test_seed, basic_mock_brain(), basic_params())
policy_eval_out = {
"action": np.array([1.0], dtype=np.float32),
"memory_out": np.array([[2.5]], dtype=np.float32),
"value": np.array([1.1], dtype=np.float32),
}
policy.evaluate = MagicMock(return_value=policy_eval_out)
brain_info_with_agents = BrainInfo([], [], [],
agents=["an-agent-id"],
local_done=[False])
result = policy.get_action(brain_info_with_agents)
expected = ActionInfo(policy_eval_out["action"], policy_eval_out["value"],
policy_eval_out)
assert result == expected
def test_take_action_returns_empty_with_no_agents():
test_seed = 3
policy = TFPolicy(test_seed, basic_mock_brain(), basic_params())
no_agent_brain_info = BrainInfo([], [], [], agents=[])
result = policy.get_action(no_agent_brain_info)
assert result == ActionInfo([], [], None)