def test_process_visual_observation():
in_array_1 = np.random.rand(128, 64, 3)
proto_obs_1 = generate_compressed_proto_obs(in_array_1)
in_array_2 = np.random.rand(128, 64, 3)
in_array_2_mapping = [0, 1, 2]
proto_obs_2 = generate_compressed_proto_obs_with_mapping(
in_array_2, in_array_2_mapping)
ap1 = AgentInfoProto()
ap1.observations.extend([proto_obs_1])
ap2 = AgentInfoProto()
ap2.observations.extend([proto_obs_2])
ap_list = [ap1, ap2]
arr = _process_maybe_compressed_observation(0, (128, 64, 3), ap_list)
assert list(arr.shape) == [2, 128, 64, 3]
assert np.allclose(arr[0, :, :, :], in_array_1, atol=0.01)
assert np.allclose(arr[1, :, :, :], in_array_2, atol=0.01)
def test_process_visual_observation_bad_shape():
in_array_1 = np.random.rand(128, 64, 3)
proto_obs_1 = generate_compressed_proto_obs(in_array_1)
ap1 = AgentInfoProto()
ap1.observations.extend([proto_obs_1])
ap_list = [ap1]
with pytest.raises(UnityObservationException):
_process_visual_observation(0, (128, 42, 3), ap_list)
def test_process_visual_observation_grayscale():
in_array_1 = np.random.rand(128, 64, 3)
proto_obs_1 = generate_compressed_proto_obs(in_array_1, grayscale=True)
expected_out_array_1 = np.mean(in_array_1, axis=2, keepdims=True)
in_array_2 = np.random.rand(128, 64, 3)
in_array_2_mapping = [0, 0, 0]
proto_obs_2 = generate_compressed_proto_obs_with_mapping(
in_array_2, in_array_2_mapping)
expected_out_array_2 = np.mean(in_array_2, axis=2, keepdims=True)
ap1 = AgentInfoProto()
ap1.observations.extend([proto_obs_1])
ap2 = AgentInfoProto()
ap2.observations.extend([proto_obs_2])
ap_list = [ap1, ap2]
arr = _process_visual_observation(0, (128, 64, 1), ap_list)
assert list(arr.shape) == [2, 128, 64, 1]
assert np.allclose(arr[0, :, :, :], expected_out_array_1, atol=0.01)
assert np.allclose(arr[1, :, :, :], expected_out_array_2, atol=0.01)
def test_process_visual_observation_bad_shape():
in_array_1 = np.random.rand(128, 64, 3)
proto_obs_1 = generate_compressed_proto_obs(in_array_1)
ap1 = AgentInfoProto()
ap1.observations.extend([proto_obs_1])
ap_list = [ap1]
shape = (128, 42, 3)
obs_spec = create_observation_specs_with_shapes([shape])[0]
with pytest.raises(UnityObservationException):
_process_maybe_compressed_observation(0, obs_spec, ap_list)
def generate_list_agent_proto(
n_agent: int,
shape: List[Tuple[int]],
infinite_rewards: bool = False,
nan_observations: bool = False,
) -> List[AgentInfoProto]:
result = []
for agent_index in range(n_agent):
ap = AgentInfoProto()
ap.reward = float("inf") if infinite_rewards else agent_index
ap.done = agent_index % 2 == 0
ap.max_step_reached = agent_index % 4 == 0
ap.id = agent_index
ap.action_mask.extend([True, False] * 5)
obs_proto_list = []
for obs_index in range(len(shape)):
obs_proto = ObservationProto()
obs_proto.shape.extend(list(shape[obs_index]))
obs_proto.compression_type = NONE
obs_proto.float_data.data.extend(
([float("nan")] if nan_observations else [0.1]) *
np.prod(shape[obs_index]))
obs_proto_list.append(obs_proto)
ap.observations.extend(obs_proto_list)
result.append(ap)
return result
def test_process_visual_observation_padded_channels():
in_array_1 = np.random.rand(128, 64, 12)
in_array_1_mapping = [0, 1, 2, 3, -1, -1, 4, 5, 6, 7, -1, -1]
proto_obs_1 = generate_compressed_proto_obs_with_mapping(
in_array_1, in_array_1_mapping)
expected_out_array_1 = np.take(in_array_1, [0, 1, 2, 3, 6, 7, 8, 9],
axis=2)
ap1 = AgentInfoProto()
ap1.observations.extend([proto_obs_1])
ap_list = [ap1]
arr = _process_visual_observation(0, (128, 64, 8), ap_list)
assert list(arr.shape) == [1, 128, 64, 8]
assert np.allclose(arr[0, :, :, :], expected_out_array_1, atol=0.01)
def proto_from_batched_step_result(
batched_step_result: BatchedStepResult
) -> List[AgentInfoProto]:
agent_info_protos: List[AgentInfoProto] = []
for agent_id in batched_step_result.agent_id:
agent_id_index = batched_step_result.agent_id_to_index[agent_id]
reward = batched_step_result.reward[agent_id_index]
done = batched_step_result.done[agent_id_index]
max_step_reached = batched_step_result.max_step[agent_id_index]
agent_mask = None
if batched_step_result.action_mask is not None:
agent_mask = [] # type: ignore
for _branch in batched_step_result.action_mask:
agent_mask = np.concatenate(
(agent_mask, _branch[agent_id_index, :]), axis=0
)
observations: List[ObservationProto] = []
for all_observations_of_type in batched_step_result.obs:
observation = all_observations_of_type[agent_id_index]
if len(observation.shape) == 3:
observations.append(generate_uncompressed_proto_obs(observation))
else:
observations.append(
ObservationProto(
float_data=ObservationProto.FloatData(data=observation),
shape=[len(observation)],
compression_type=NONE,
)
)
agent_info_proto = AgentInfoProto(
reward=reward,
done=done,
id=agent_id,
max_step_reached=max_step_reached,
action_mask=agent_mask,
observations=observations,
)
agent_info_protos.append(agent_info_proto)
return agent_info_protos
def proto_from_steps(decision_steps: DecisionSteps,
terminal_steps: TerminalSteps) -> List[AgentInfoProto]:
agent_info_protos: List[AgentInfoProto] = []
# Take care of the DecisionSteps first
for agent_id in decision_steps.agent_id:
agent_id_index = decision_steps.agent_id_to_index[agent_id]
reward = decision_steps.reward[agent_id_index]
done = False
max_step_reached = False
agent_mask: Any = None
if decision_steps.action_mask is not None:
agent_mask = []
for _branch in decision_steps.action_mask:
agent_mask = np.concatenate(
(agent_mask, _branch[agent_id_index, :]), axis=0)
agent_mask = agent_mask.astype(np.bool).tolist()
observations: List[ObservationProto] = []
for all_observations_of_type in decision_steps.obs:
observation = all_observations_of_type[agent_id_index]
if len(observation.shape) == 3:
observations.append(
generate_uncompressed_proto_obs(observation))
else:
observations.append(
ObservationProto(
float_data=ObservationProto.FloatData(
data=observation),
shape=[len(observation)],
compression_type=NONE,
))
agent_info_proto = AgentInfoProto(
reward=reward,
done=done,
id=agent_id,
max_step_reached=bool(max_step_reached),
action_mask=agent_mask,
observations=observations,
)
agent_info_protos.append(agent_info_proto)
# Take care of the TerminalSteps second
for agent_id in terminal_steps.agent_id:
agent_id_index = terminal_steps.agent_id_to_index[agent_id]
reward = terminal_steps.reward[agent_id_index]
done = True
max_step_reached = terminal_steps.interrupted[agent_id_index]
final_observations: List[ObservationProto] = []
for all_observations_of_type in terminal_steps.obs:
observation = all_observations_of_type[agent_id_index]
if len(observation.shape) == 3:
final_observations.append(
generate_uncompressed_proto_obs(observation))
else:
final_observations.append(
ObservationProto(
float_data=ObservationProto.FloatData(
data=observation),
shape=[len(observation)],
compression_type=NONE,
))
agent_info_proto = AgentInfoProto(
reward=reward,
done=done,
id=agent_id,
max_step_reached=bool(max_step_reached),
action_mask=None,
observations=final_observations,
)
agent_info_protos.append(agent_info_proto)
return agent_info_protos
