How does bayesopt() handle integer optimizable variables?

The variable types of optimizableVariable objects include real, integer, and categorical. Can someone explain how is the integer variables handled in bayesopt() ? Simply round-off the 'real' values to the closest "integer" values? Is there any reference to support this development in bayesopt()?

Answer 1

[BhaTTa]

Hey @Wei Song, Please refer to this answer: https://www.mathworks.com/matlabcentral/answers/454604