def _build_buffer(self):
if self.use_priority:
from rls.memories.per_buffer import PrioritizedDataBuffer
buffer = PrioritizedDataBuffer(n_copies=self.n_copies,
batch_size=self.batch_size,
buffer_size=self.buffer_size,
chunk_length=self._chunk_length,
max_train_step=self._max_train_step,
**load_config(f'rls/configs/buffer/off_policy_buffer.yaml')[
'PrioritizedDataBuffer'])
else:
from rls.memories.er_buffer import DataBuffer
buffer = DataBuffer(n_copies=self.n_copies,
batch_size=self.batch_size,
buffer_size=self.buffer_size,
chunk_length=self._chunk_length)
return buffer
def UpdateConfig(config: Dict, file_path: str, key_name: str = 'algo') -> Dict:
'''
update configurations from a readable file.
params:
config: current configurations
file_path: path of configuration file that needs to be loaded
key_name: a specified key in configuration file that needs to update current configurations
return:
config: updated configurations
'''
_config = load_config(file_path)
key_values = _config[key_name]
try:
for key in key_values:
config[key] = key_values[key]
except Exception as e:
logger.info(e)
sys.exit()
return config
def __init__(self,
worker_id=0,
file_name=None,
port=5005,
render=False,
seed=42,
timeout_wait=60,
env_copies=12,
env_name='3DBall',
real_done=True,
initialize_config={},
engine_config={
'width': 84,
'height': 84,
'quality_level': 5,
'time_scale': 20,
'target_frame_rate': -1,
'capture_frame_rate': 60
},
**kwargs):
self._n_copies = env_copies
self._real_done = real_done
self._side_channels = self.initialize_all_side_channels(
initialize_config, engine_config)
env_kwargs = dict(seed=seed,
worker_id=worker_id,
timeout_wait=timeout_wait,
side_channels=list(
self._side_channels.values())) # 注册所有初始化后的通讯频道
if file_name is not None:
env_dict = load_config('rls/configs/unity/env_dict.yaml')
env_kwargs.update(file_name=file_name,
base_port=port,
no_graphics=not render,
additional_args=[
'--scene',
str(env_dict.get(env_name, 'None'))
])
self.env = UnityEnvironment(**env_kwargs)
self.env.reset()
self.initialize_environment()