in mtrl/agent/hipbmdp.py [0:0]
def __init__(
self,
env_obs_shape: List[int],
action_shape: List[int],
action_range: Tuple[int, int],
device: torch.device,
actor_cfg: ConfigType,
critic_cfg: ConfigType,
decoder_cfg: ConfigType,
reward_decoder_cfg: ConfigType,
transition_model_cfg: ConfigType,
alpha_optimizer_cfg: ConfigType,
actor_optimizer_cfg: ConfigType,
critic_optimizer_cfg: ConfigType,
multitask_cfg: ConfigType,
decoder_optimizer_cfg: ConfigType,
encoder_optimizer_cfg: ConfigType,
reward_decoder_optimizer_cfg: ConfigType,
transition_model_optimizer_cfg: ConfigType,
discount: float = 0.99,
init_temperature: float = 0.01,
actor_update_freq: int = 2,
critic_tau: float = 0.005,
critic_target_update_freq: int = 2,
encoder_tau: float = 0.005,
loss_reduction: str = "mean",
decoder_update_freq: int = 1,
decoder_latent_lambda: float = 0.0,
cfg_to_load_model: Optional[ConfigType] = None,
should_complete_init: bool = True,