back to main page

Results of the GECCO'2019 2-OBJ Track

"Raw" Result Data

On each problem participants were judged by the overall dominated hypervolume within the given budget of function evaluations. There were 3 participants in the field. The best function value per problem and participant (1000 times 3 double precision numbers) is listed in this text file.

Participant Ranking

Participants were ranked based on aggregated problem-wise ranks (details here and here). The following results table lists participants with overall scores (higher is better) and the sum of ranks over all problems (lower is better) The table can be sorted w.r.t. these criteria.

rank participant method name method description software paper score  sum of ranks 
1 Nacim Belkhir 476.885 1412
2 Artelys 124.073 2258
3 Thomas Wortmann, Roger Ko, Chu Wy Ton RBFMOpt This method is a prototypical extension of the single-objective, model-based algorithm RBFOpt ( Similar to ParEGO, RBFMOpt repeatedly runs RBFOpt to optimize different weighted sums in order to approximate the Pareto front. The weights are drawn from a non-discrepancy sequence.
In other words, the method uses conventional scalarizing, but, as a model-based algorithm, RBFOpt can benefit from and build on good solutions found in previous runs.
92.1886 2330

Visualization of Performance Data

The following figure shows an aggregated view on the performance data.

The following figures show the same data, but separately for each problem dimension.