Counterplanning using Goal Recognition and Landmarks

Authors: Alberto Pozanco, Yolanda E-Martín, Susana Fernández, Daniel Borrajo

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results in several domains show the benefits of our novel approach.
Researcher Affiliation Academia Alberto Pozanco, Yolanda E-Mart ın, Susana Fern andez, Daniel Borrajo Departamento de Inform atica, Universidad Carlos III de Madrid Avda. de la Universidad, 30. 28911 Legan es, Madrid, Spain
Pseudocode Yes Algorithm 1 DOMAIN-INDEPENDENT COUNTERPLANNING
Open Source Code No The paper does not provide any explicit statements about releasing source code for the methodology described, nor does it include links to a code repository.
Open Datasets Yes We empirically evaluate our approach on the new previously described TERRORIST domain as well as in other domains usually used in goal recognition works such as LOGISTICS, EASY IPC GRID, BLOCKS, and INTRUSION DETECTION.
Dataset Splits No The paper mentions generating '10 random problems' for each domain and varying 'observed actions' percentage, but it does not specify explicit training, validation, or test dataset splits needed for reproduction.
Hardware Specification Yes All the experiments were ran on a Ubuntu machine with Intel Core 2 Quad Q8400 running at 2.66 GHz.
Software Dependencies No The paper mentions using specific planners like 'HSP*f [Haslum, 2008]' and 'LAMA [Richter et al., 2011]', but it does not provide specific version numbers for these software components.
Experiment Setup Yes The planning times for all the planners were set to 1800 seconds. In all the domains πφ is computed using GREEDY LAMA. For optimal plan computations of FCL, we use HSP*f. The set of candidate goals Gφ always consists of a 20% of all the possible goals in each problem. The set of observed actions was taken to be a subset of the plan solution πφ, ranging from 10% of the actions, up to 70% of the actions.