Human-Aware Plan Recognition
Authors: Hankz Zhuo
AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In the experiment, we evaluate our approach in three planning domains to demonstrate its effectiveness. To evaluate the effectiveness of our algorithm, we built a system to simulate real-world applications and synthesized training and testing data. |
| Researcher Affiliation | Academia | Hankz Hankui Zhuo Department of Computer Science, Sun Yat-Sen University, Guangzhou, China. 510006 zhuohank@mail.sysu.edu.cn |
| Pseudocode | Yes | Algorithm 1 An overview of our HARE algorithm |
| Open Source Code | No | The paper does not provide an explicit statement or link to the open-source code for the methodology described. |
| Open Datasets | Yes | We generated data in three planning domains blocks2, depots3, and driverlog3.. The reason why we used planning domains is it is simple to generate plans by running an off-the-shelf planner. (Footnotes point to URLs: 2http://www.cs.toronto.edu/aips2000/, 3http://www.cs.cmu.edu/afs/cs/project/jair/pub/volume20/ long03a-html/JAIRIPC.html, 4https://fai.cs.uni-saarland.de/hoffmann/ff.html) |
| Dataset Splits | No | The paper mentions generating 'training and testing data' but does not provide specific details on how the dataset was split into training, validation, and test sets (e.g., percentages or counts for each split). |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU/CPU models, memory, or processor types used for running the experiments. |
| Software Dependencies | No | The paper mentions 'FF' and 'Max HS' but does not provide specific version numbers for these or any other software dependencies. |
| Experiment Setup | Yes | We set the window of training context c in Equation (1) to be three, constants λ1 and λ2 in Equation 3 to be 0.5, and number of observed actions to be 20 for each observed action sequence. We set the context window c used in Equation (1) to be three, the constants λ1 and λ2 in Equation 3 to be 0.5 and the ratio of rating scores R to be 0.15. |