Social Planning: Achieving Goals by Altering Others’ Mental States

Authors: Chris Pearce, Ben Meadows, Pat Langley, Mike Barley

AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We report the results for experiments on social scenarios that involve different levels of sophistication and that demonstrate both SFPS s capabilities and the sources of its power.
Researcher Affiliation Academia Chris Pearce and Ben Meadows and Pat Langley and Mike Barley Department of Computer Science, University of Auckland Private Bag 92019, Auckland 1142, New Zealand
Pseudocode No The paper describes the problem-solving architecture and operators but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link regarding the public availability of source code for the described methodology.
Open Datasets No The paper states 'We have developed scenarios similar to Aesop s fables to study this cognitive ability.' and presents them in Table 1. There is no explicit mention of these scenarios being publicly available as a dataset, nor any citation to an external public dataset.
Dataset Splits No The paper mentions running the system '50 times on each of the eight problems' but does not specify any training, validation, or test dataset splits in terms of percentages, sample counts, or predefined splits.
Hardware Specification No The paper does not provide specific details on the hardware (e.g., CPU, GPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions implementing ideas 'within the FPS problem-solving architecture (Langley et al. 2013)' but does not provide specific version numbers for FPS or any other software dependencies like programming languages or libraries.
Experiment Setup Yes We consider runs that generate plans violating this condition, or that exceed 10,000 cycles, to be failures. SFPS is nondeterministic, in that it selects intentions probabilistically, so we ran it 50 times on each of the eight problems and report summary results from these runs. For our work on social planning, we incorporated strategic knowledge that combines iterative-sampling search, backward chaining, and eager commitment methods.