def create_bc_module(mock_behavior_specs, bc_settings, use_rnn, tanhresample):
# model_path = env.external_brain_names[0]
trainer_config = TrainerSettings()
trainer_config.network_settings.memory = (NetworkSettings.MemorySettings()
if use_rnn else None)
policy = TorchPolicy(0, mock_behavior_specs, trainer_config, tanhresample,
tanhresample)
bc_module = BCModule(
policy,
settings=bc_settings,
policy_learning_rate=trainer_config.hyperparameters.learning_rate,
default_batch_size=trainer_config.hyperparameters.batch_size,
default_num_epoch=3,
)
return bc_module
def __init__(self, policy: TorchPolicy, trainer_settings: TrainerSettings):
super().__init__()
self.policy = policy
self.trainer_settings = trainer_settings
self.update_dict: Dict[str, torch.Tensor] = {}
self.value_heads: Dict[str, torch.Tensor] = {}
self.memory_in: torch.Tensor = None
self.memory_out: torch.Tensor = None
self.m_size: int = 0
self.global_step = torch.tensor(0)
self.bc_module: Optional[BCModule] = None
self.create_reward_signals(trainer_settings.reward_signals)
if trainer_settings.behavioral_cloning is not None:
self.bc_module = BCModule(
self.policy,
trainer_settings.behavioral_cloning,
policy_learning_rate=trainer_settings.hyperparameters.learning_rate,
default_batch_size=trainer_settings.hyperparameters.batch_size,
default_num_epoch=3,
)