Constructing Symbolic Representations for High-Level Planning
Authors: George Konidaris, Leslie Kaelbling, Tomas Lozano-Perez
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We tested planning on three goals, each starting from the set of all states where the monkey is not crying out and the lights and music are off. We implemented a breadthfirst symbol algebra planner in Java, and also used the automatically generated PDDL description as input to the FF planner (Hoffmann and Nebel 2001). Timing results, given in Table 1, show that both systems can solve the resulting search problem very quickly |
| Researcher Affiliation | Academia | George Konidaris, Leslie Pack Kaelbling and Tomas Lozano-Perez MIT Computer Science and Artificial Intelligence Laboratory 32 Vassar Street, Cambridge MA 02139 USA {gdk, lpk, tlp}@csail.mit.edu |
| Pseudocode | No | The paper describes methods and processes in narrative text and figures but does not include explicit pseudocode blocks or algorithm listings. |
| Open Source Code | No | The paper does not provide any statement about making its code open source or include any links to code repositories. |
| Open Datasets | No | The paper mentions collecting '5,000 positive and negative examples' within the 'continuous playroom domain' but does not specify a publicly available dataset by name with a citation, link, or repository for direct access to these examples. |
| Dataset Splits | No | The paper mentions gathering 5,000 examples for symbol acquisition and using the WEKA toolkit, but it does not specify explicit training, validation, or test dataset splits (e.g., percentages, sample counts, or methodology for predefined splits). |
| Hardware Specification | Yes | Results were obtained on a 2.5Ghz Intel Core i5 processor and 8GB of RAM. |
| Software Dependencies | No | The paper mentions using the 'WEKA toolkit (Hall et al. 2009) C4.5 decision tree (Quinlan 1993)' and the 'FF planner (Hoffmann and Nebel 2001)', but it does not provide specific version numbers for these software dependencies. |
| Experiment Setup | No | While the paper describes the 'continuous playroom domain' and the general process of data collection and symbol learning, it does not provide specific experimental setup details such as hyperparameters for the C4.5 decision tree (e.g., pruning settings, confidence factor) or other training configurations for the planners. |