ray.rllib.models.distributions.Distribution.logp#

abstract Distribution.logp(value: numpy.array | jnp.ndarray | tf.Tensor | torch.Tensor, **kwargs) → numpy.array | jnp.ndarray | tf.Tensor | torch.Tensor[source]#

The log-likelihood of the distribution computed at value

Parameters:

  • value – The value to compute the log-likelihood at.

  • **kwargs – Forward compatibility placeholder.

Returns:

The log-likelihood of the value.