Function _loss_value

advanced_source/coding_ddpg.py:312–342

(
    self,
    tensordict,
)

def _loss_value(
    self,
    tensordict,
):
    td_copy = tensordict.clone()

    # V(s, a)
    with self.value_network_params.to_module(self.value_network):
        self.value_network(td_copy)
    pred_val = td_copy.get("state_action_value").squeeze(-1)

    # we manually reconstruct the parameters of the actor-critic, where the first
    # set of parameters belongs to the actor and the second to the value function.
    target_params = TensorDict(
        {
            "module": {
                "0": self.target_actor_network_params,
                "1": self.target_value_network_params,
            }
        },
        batch_size=self.target_actor_network_params.batch_size,
        device=self.target_actor_network_params.device,
    )
    with target_params.to_module(self.actor_critic):
        target_value = self.value_estimator.value_estimate(tensordict).squeeze(-1)

    # Computes the value loss: L2, L1 or smooth L1 depending on `self.loss_function`
    loss_value = distance_loss(pred_val, target_value, loss_function=self.loss_function)
    td_error = (pred_val - target_value).pow(2)

    return loss_value, td_error, pred_val, target_value


###############################################################################