tf_agents.bandits.policies.loss_utils.pinball_loss

Adds a Pinball loss for quantile regression.

tf_agents.bandits.policies.loss_utils.pinball_loss(
    y_true: tf_agents.typing.types.Tensor,
    y_pred: tf_agents.typing.types.Tensor,
    weights: tf_agents.typing.types.Float = 1.0,
    scope: Optional[Text] = None,
    loss_collection: tf.compat.v1.GraphKeys = tf.compat.v1.GraphKeys.LOSSES,
    reduction: tf.compat.v1.losses.Reduction = tf.compat.v1.losses.Reduction.SUM_BY_NONZERO_WEIGHTS,
    quantile: float = 0.5
) -> tf_agents.typing.types.Float

loss = quantile * (y_true - y_pred)         if y_true > y_pred
loss = (quantile - 1) * (y_true - y_pred)   otherwise
```

See: <a href="https://en.wikipedia.org/wiki/Quantile_regression#Quantiles">https://en.wikipedia.org/wiki/Quantile_regression#Quantiles</a>


`weights` acts as a coefficient for the loss. If a scalar is provided, then
the loss is simply scaled by the given value. If `weights` is a tensor of size
`[batch_size]`, then the total loss for each sample of the batch is rescaled
by the corresponding element in the `weights` vector. If the shape of
`weights` matches the shape of `predictions`, then the loss of each
measurable element of `predictions` is scaled by the corresponding value of
`weights`.

<!-- Tabular view -->
 <table class="responsive fixed orange">
<colgroup><col width="214px"><col></colgroup>
<tr><th colspan="2"><h2 class="add-link">Args</h2></th></tr>

<tr>
<td>
`y_true`
</td>
<td>
tensor of true targets.
</td>
</tr><tr>
<td>
`y_pred`
</td>
<td>
tensor of predicted targets.
</td>
</tr><tr>
<td>
`weights`
</td>
<td>
Optional `Tensor` whose rank is either 0, or the same rank as
`labels`, and must be broadcastable to `labels` (i.e., all dimensions must
be either `1`, or the same as the corresponding `losses` dimension).
</td>
</tr><tr>
<td>
`scope`
</td>
<td>
The scope for the operations performed in computing the loss.
</td>
</tr><tr>
<td>
`loss_collection`
</td>
<td>
collection to which the loss will be added.
</td>
</tr><tr>
<td>
`reduction`
</td>
<td>
Type of reduction to apply to loss.
</td>
</tr><tr>
<td>
`quantile`
</td>
<td>
A float between 0. and 1., the quantile we want to regress.
</td>
</tr>
</table>



<!-- Tabular view -->
 <table class="responsive fixed orange">
<colgroup><col width="214px"><col></colgroup>
<tr><th colspan="2"><h2 class="add-link">Returns</h2></th></tr>
<tr class="alt">
<td colspan="2">
Weighted Pinball loss float `Tensor`. If `reduction` is `NONE`, this has the
same shape as `labels`; otherwise, it is scalar.
</td>
</tr>

</table>



<!-- Tabular view -->
 <table class="responsive fixed orange">
<colgroup><col width="214px"><col></colgroup>
<tr><th colspan="2"><h2 class="add-link">Raises</h2></th></tr>

<tr>
<td>
`ValueError`
</td>
<td>
If the shape of `predictions` doesn't match that of `labels` or
if the shape of `weights` is invalid.  Also if `labels` or `predictions`
is None.
</td>
</tr>
</table>




#### Eager Compatibility
The `loss_collection` argument is ignored when executing eagerly. Consider
holding on to the return value or collecting losses via a <a href="https://www.tensorflow.org/api_docs/python/tf/keras/Model"><code>tf.keras.Model</code></a>.