Privacy Preserving Plans in Partially Observable Environments

Authors: Sarah Keren, Avigdor Gal, Erez Karpas

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our empirical evaluation shows the feasibility of the proposed solution. and Empirical evaluation is presented in Section 5
Researcher Affiliation Academia Technion Israel Institute of Technology and {sarahn@tx,avigal@ie,karpase@}.technion.ac.il
Pseudocode Yes Figure 2: The common-declare compilation which describes the planning problem P' and its components in a structured, definitional format, including actions and costs.
Open Source Code No The paper does not provide any specific links or explicit statements about the availability of open-source code for the described methodology.
Open Datasets Yes We used 20 problems from the LOGISTICS (LOG) domain and 12 from the BLOCKSWORLD domain (BLOCK), which were shown to be the most computationally challenging for goal recognition design in previous work [Keren et al., 2016] and 34 GRIDNAVIGATION (GRID) problems of size 25 25.
Dataset Splits No The paper does not provide specific dataset split information (like train/validation/test percentages or sample counts). It refers to sets of 'problems' from planning domains which are evaluated, but not split.
Hardware Specification Yes Experiments were run on Intel(R) Xeon(R) CPU X5690 machines, with a time limit of 30 minutes and memory limit of 2 GB.
Software Dependencies No The paper mentions using 'the Fast Downward planning system [Helmert, 2006] running A with the LM-CUT heuristic [Helmert and Domshlak, 2009]' but does not provide specific version numbers for these software components.
Experiment Setup Yes For each problem, we created 5 versions: Fully observable (FULL), Non observable actions (NO), Partially observable deterministic (POD), Partially observable non-deterministic (POND)... We compared three compilations: latest Split (LS) [Keren et al., 2014], latest Expose (LE) [Keren et al., 2016], and common-declare (CD)... We used the Fast Downward planning system [Helmert, 2006] running A with the LM-CUT heuristic [Helmert and Domshlak, 2009].