def __init__(self, xml, port):
InstanceManager.configure_malmo_base_port(port)
self.action_to_command_array = [
'move 1', 'camera 0 270', 'camera 0 90'
]
super().__init__(
xml,
gym.spaces.Box(low=0, high=255, shape=(84, 84, 3), dtype=np.uint8),
gym.spaces.Discrete(3))
self.metadata['video.frames_per_second'] = 2
def __init__(
self,
seeds: [int],
file_name: Optional[str] = None,
worker_id: int = 0,
base_port: int = 5005,
docker_training: bool = False,
no_graphics: bool = False,
# timeout_wait: int = 30,
# args: Optional[List[str]] = None,
num_envs: int = 1):
"""
Starts a new unity environment and establishes a connection with the environment.
Notice: Currently communication between Unity and Python takes place over an open socket without authentication.
Ensure that the network where training takes place is secure.
:string file_name: Name of Unity environment binary.
:int base_port: Baseline port number to connect to Unity environment over. worker_id increments over this.
:int worker_id: Number to add to communication port (5005) [0]. Used for asynchronous agent scenarios.
:bool docker_training: Informs this class whether the process is being run within a container.
:bool no_graphics: Whether to run the Unity simulator in no-graphics mode
:int timeout_wait: Time (in seconds) to wait for connection from environment.
:bool train_mode: Whether to run in training mode, speeding up the simulation, by default.
"""
atexit.register(self._close)
self.port = base_port + worker_id
self._buffer_size = 12000
self._version_ = "API-10"
self._loaded = (
False
) # If true, this means the environment was successfully loaded
self.proc1 = (
None
) # The process that is started. If None, no process was started
# self.communicator = self.get_communicator(worker_id, base_port, timeout_wait)
self._worker_id = worker_id
self._is_first_message = True
from minerl.env.malmo import InstanceManager
self._envs: Dict[str, [Env]] = {}
self._agent_ids: Dict[str, [str]] = {}
self._n_agents: Dict[str, int] = {}
self._academy_name = 'MineRLUnityAcademy'
self._log_path = 'log_path'
self._brains: Dict[str, BrainParameters] = {}
self._brain_names: List[str] = []
self._external_brain_names: List[str] = []
InstanceManager.configure_malmo_base_port(base_port + worker_id)
for i in range(num_envs):
print('InstanceManager:', InstanceManager)
try:
print('.MAXINSTANCES', InstanceManager.MAXINSTANCES)
except AttributeError:
print('.MAXINSTANCES', 'None')
pass
print('.REMOTE', InstanceManager.is_remote())
try:
print('.ninstances', InstanceManager.ninstances)
except AttributeError:
print('.ninstances', 'None')
pass
try:
print('.DEFAULT_IP', InstanceManager.DEFAULT_IP)
except AttributeError:
print('.DEFAULT_IP', 'None')
pass
env = gym.make(file_name)
env = MineRLToMLAgentWrapper(env, seeds[i])
env = RefineObservationsWrapper(env)
env = NormalizeObservationsWrapper(env)
VISUALIZE = bool(os.getenv('VISUALIZE', None))
if VISUALIZE and self.worker_id is 0:
env = KeyboardControlWrapper(env)
# env = HardwireActionsWrapper(env)
env = PruneActionsWrapper(
env,
[
# 'attack_jump'
# ,'camera_left_right'
# 'camera_up_down'
# ,'forward_back'
# 'left_right'
# ,'place'
# ,'sneak_sprint'
])
env = PruneVisualObservationsWrapper(env, hack_ignor=True)
# env = VisualObsAsFloatWrapper(env)
env = FrameStackMono(env, 2, 10)
EVALUATION_STAGE = os.getenv('EVALUATION_STAGE', '')
if EVALUATION_STAGE != 'testing':
env = EarlyExitWrapper(env)
env = DingRewardOnDoneWrapper(env)
# note: should be the last wrapper
env = ResetOnDoneWrapper(env)
MineRLToMLAgentWrapper.set_wrappers_for_pretraining(file_name, env)
brain_name = env.brain_parameters.brain_name
if brain_name not in self._agent_ids:
self._envs[brain_name] = []
self._agent_ids[brain_name] = []
self._n_agents[brain_name] = 0
self._brain_names.append(brain_name)
brain = env.brain_parameters
self._external_brain_names.append(brain_name)
self._brains[brain_name] = brain
self._envs[brain_name].append(env)
self._agent_ids[brain_name].append(env.agent_id)
self._n_agents[brain_name] += 1
self._loaded = True
self._num_brains = len(self._brain_names)
self._num_external_brains = len(self._external_brain_names)
# self._resetParameters = dict(aca_params.environment_parameters.float_parameters)
self._resetParameters = dict()
logger.info("\n'{0}' started successfully!\n{1}".format(
self._academy_name, str(self)))
if self._num_external_brains == 0:
logger.warning(
" No Learning Brains set to train found in the Unity Environment. "
"You will not be able to pass actions to your agent(s).")