Landmark-Based Heuristics for Goal Recognition

Authors: Ramon Pereira, Nir Oren, Felipe Meneguzzi

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically evaluate these heuristics over both standard goal/plan recognition problems, and a set of very large problems.
Researcher Affiliation Academia Ramon Fraga Pereira, Nir Oren, Felipe Meneguzzi Pontifical Catholic University of Rio Grande do Sul, Brazil ramon.pereira@acad.pucrs.br felipe.meneguzzi@pucrs.br University of Aberdeen, United Kingdom n.oren@abdn.ac.uk
Pseudocode Yes Algorithm 1 Compute Achieved Landmarks From Observations. Input: I initial state, G set of candidate goals, O observations, and LG goals and their extracted landmarks. Output: A map of goals to their achieved landmarks.
Open Source Code No The paper mentions using 'open-source planners, such as FAST-DOWNWARD, FAST-FORWARD, and LAMA', but it does not provide a link or statement about open-sourcing its own developed methodology's code.
Open Datasets Yes We empirically evaluate our approach using datasets created using 15 domains from the planning literature1. http://ipc.icaps-conference.org
Dataset Splits No The paper describes evaluating on datasets with 'partial observation sequences represent plans for G where 10%, 30%, 50% or 70% of actions are observed', which relates to observation completeness, not a train/validation/test split of the dataset itself.
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments (e.g., CPU/GPU models, memory).
Software Dependencies No The paper mentions using 'open-source planners, such as FAST-DOWNWARD, FAST-FORWARD, and LAMA', but it does not specify the version numbers for these or any other software dependencies.
Experiment Setup No The paper does not provide specific experimental setup details such as hyperparameter values, training configurations, or system-level settings.