Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary

Authors: Masataro Asai, Alex Fukunaga

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

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate Lat Plan using image-based versions of 3 planning domains: 8-puzzle, Towers of Hanoi and Lights Out.
Researcher Affiliation Academia Masataro Asai, Alex Fukunaga Graduate School of Arts and Sciences The University of Tokyo
Pseudocode No The paper describes algorithmic steps but does not include formal pseudocode blocks or algorithms labeled as such.
Open Source Code Yes Latplan code is available on Github.
Open Datasets Yes MNIST 8-puzzle is an image-based version of the 8-puzzle, where tiles contain hand-written digits (0-9) from the MNIST database (Le Cun et al. 1998).
Dataset Splits No The paper mentions training various components (SAE, AAE, AD, SD) but does not specify explicit training, validation, and test splits for the data used in training the models.
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments (e.g., CPU/GPU models, memory specifications).
Software Dependencies No The paper mentions using "a modified version of Fast Downward (Helmert 2006)" but does not specify its version number or any other software dependencies with their respective versions.
Experiment Setup No The paper describes the general training processes (e.g., minimizing reconstruction loss, annealing Gumbel-Softmax temperature) but does not provide specific hyperparameter values like learning rates, batch sizes, or explicit training schedules.