population
|
Tensor or Python list of Tensor s representing the
current population vectors. Each Tensor must be of the same real dtype.
The first dimension indexes individual population members while the
rest of the dimensions are consumed by the value function. For example,
if the population is a single Tensor of shape [n, m1, m2], then n is
the population size and the output of objective_function applied to the
population is a Tensor of shape [n]. If the population is a python
list of Tensor s then each Tensor in the list should have the first
axis of a common size, say n and objective_function(*population)
should return a Tensor of shape [n]. The population must have at least
4 members for the algorithm to work correctly.
</td>
</tr><tr>
<td>
population_values
</td>
<td>
A Tensorof rank 1 and real dtype. The result of
applying objective_functionto the population. If not supplied it is
computed using the objective_function.
Default value: None.
</td>
</tr><tr>
<td>
differential_weight
</td>
<td>
Real scalar Tensor. Must be positive and less than
2.0. The parameter controlling the strength of mutation.
Default value: 0.5
</td>
</tr><tr>
<td>
crossover_prob
</td>
<td>
Real scalar Tensor. Must be between 0 and 1. The
probability of recombination per site.
Default value: 0.9
</td>
</tr><tr>
<td>
seed
</td>
<td>
intor None. The random seed for this Op. If None, no seed is
applied.
Default value: None.
</td>
</tr><tr>
<td>
name`
|
(Optional) Python str. The name prefixed to the ops created by this
function. If not supplied, the default name 'one_step' is
used.
Default value: None
|