Portfolio

IBaCoP (IPC-2014)

Published:

IBaCoP is the result of applying the Pareto efficiency technique (Censor 1977) to select a sub-set of planners from the planners in sequential satisficing track plus LPG-td. We select the planners that dominates all others in at least one domain (from a set of training domains), taking into account quality and time. We assign the same running time for all selected planners

IBaCoP2 (IPC-2014)

Published:

IBaCoP2 is a portfolio auto configurable with a classification model

IBaCoP (IPC-2018)

Published:

IBaCoP family of planning portfolios submitted to the International Planning Competition 2018. Our portfolios are improved versions of the planners submitted to the last IPC-2014. IBaCoP-2018 is configured following a Pareto efficiency approach for selecting planners and then giving the same execution time for the selected planners. IBaCoP2-2018 decides for each problem the sub-set of planners to use. This decision is based on predictive models trained with domain/problems from previous IPCs. Both 2018 portfolios compete in the sequential satisficing and agile tracks.