1.6.0

• Support newer versions of dependencies, including NumPy 2

1.5.7

• Fixed a bug with display metrics in case there are no feasible points for some of the optimization algorithms

1.5.6

• Added citation to the paper in the Journal of Global Optimization
• Support pymoo 0.6.1.6: random state was not managed globally by pymoo anymore, implemented backwards compatible fixes
• Upgraded ConfigSpace to 1.2.1 (ConfigSpace below 1.0 is not supported anymore)
• Test SBArchOpt on newer Python versions

1.5.5

• Better support for using ArchOptProblemBase as a stub problem
• Fix bug in updating SEGOMOE's population

1.5.4

• Added compatibility with SMT 2.8
• Periodically rerun tests

1.5.3

• Fix some tests
• Update paper references
• Move turbofan problem data out of the repository/package

1.5.2

• Also update cumulative pop when not storing results
• Added logo
• Constrain numpy to 1.x for now

1.5.1

• Add SEGOMOE ask-tell interface and pymoo Algorithm
• Updated to pymoo 0.6.1

1.5.0

• Update to Trieste 2.0
• Add OSS license checks for dependencies
• Updated SEGOMOE integration

1.4.0

• Improved hierarchical sampling by randomizing group selection
• Display population statistics (non-failed, feasible, optimal points)
• Do not use problem-specific correction by default
• Fixed bug with problems needing correction of continuous variables and using an auto corrector
• Added correction ratio metric to problem statistics
• Fixed bug with ArchSBO running on a problem with an explicit design space
• Added interface to the Egor optimizer (#11)
• Switch to random forest classifier as default hidden constraint strategy for ArchSBO

Test problems:

• Added bi-objective version of the realistic turbofan test problem
• Added surrogate model version of the simple turbofan test problem
• Added multi-stage rocket design problem
• Added mixed-discrete versions of the GNC problem