Learning Unknown Event Models
Authors: Matthew Molineaux, David Aha
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We instantiate these approaches in a new goal reasoning agent (named FOOLMETWICE), investigate its performance in simulation studies, and report that it produces plans with significantly reduced execution cost in comparison to not learning models for surprising events. |
| Researcher Affiliation | Collaboration | Matthew Molineaux1 and David W. Aha2 1Knexus Research Corporation, Springfield, VA; 2Naval Research Laboratory, Code 5514; Washington, DC |
| Pseudocode | No | The paper describes methods and processes in text but does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code or links to a code repository for the described methodology. |
| Open Datasets | No | For each domain, we randomly generated 50 training and 25 test scenarios. In Satellites, the initial state of each scenario has 3 satellites with 12 instruments randomly apportioned among them. Each scenario has 5 goals requiring that an image of a random target be obtained in a random spectrum. Mud World scenarios consist of a 6x6 grid with random start and destination locations, each of which may contain mud with 40% probability. |
| Dataset Splits | No | The paper mentions '50 training and 25 test scenarios' but does not specify a separate validation set or provide explicit split percentages or counts for training/validation/test splits. |
| Hardware Specification | No | The paper does not provide any specific hardware details (e.g., GPU/CPU models, memory specifications) used for running the experiments. |
| Software Dependencies | No | The paper mentions using a 'SHOP2 (Nau et al., 2003) variant' and adapted 'FOIL (Quinlan, 1990)' as 'FOIL-PS', but it does not specify any version numbers for these or other software dependencies. |
| Experiment Setup | Yes | In Satellites, the initial state of each scenario has 3 satellites with 12 instruments randomly apportioned among them. Each scenario has 5 goals requiring that an image of a random target be obtained in a random spectrum. Mud World scenarios consist of a 6x6 grid with random start and destination locations, each of which may contain mud with 40% probability. We selected start and destination locations so that all routes between them contain at least 4 steps, irrespective of mud. |