tf_agents.bandits.agents.utils.compute_pairwise_distances

Compute the pairwise distances matrix.

tf_agents.bandits.agents.utils.compute_pairwise_distances(
    input_vecs: tf_agents.typing.types.Tensor
) -> tf_agents.typing.types.Tensor

Given input embedding vectors, this utility computes the (squared) pairwise distances matrix.

Args
`input_vecs`	a `Tensor`. Input embedding vectors (one per row).

Returns
The (squared) pairwise distances matrix. A dense float `Tensor` of shape [`num_vectors`, `num_vectors`], where `num_vectors` is the number of input embedding vectors.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2024-04-26 UTC.

Args