Features, Projections, and Representation Change for Generalized Planning
Authors: Blai Bonet, Hector Geffner
IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The My ND planner yields the policy below in 54 milliseconds, which from Theorem 12, is a solution of Qmove: |
| Researcher Affiliation | Academia | 1 Universidad Sim on Bol ıvar, Caracas, Venezuela 2 ICREA & Universitat Pompeu Fabra, Barcelona, Spain |
| Pseudocode | No | The paper describes methods textually and with formulas, but does not include any labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | Blocksworld, Rectangular Grids, Sliding Puzzles are standard planning domains used for experiments, which are publicly known benchmarks in the AI planning community. |
| Dataset Splits | No | The paper discusses generalized planning problems and policy computation using FOND planners, which does not involve explicit training/validation/test dataset splits in the conventional machine learning sense. |
| Hardware Specification | Yes | Experiments were done on an Intel i5-4670 CPU with 8Gb of RAM. |
| Software Dependencies | No | The paper mentions specific FOND planners (My ND, FOND-SAT-based planner) but does not provide their version numbers. |
| Experiment Setup | No | The paper describes the problem transformations (Feature Projection, Boolean Projection) and abstract actions, which define the planning problem structure, but does not specify experimental setup details such as hyperparameters, learning rates, or batch sizes relevant for training machine learning models. |