Constructing Abstraction Hierarchies Using a Skill-Symbol Loop
Authors: George Konidaris
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We describe how such a hierarchy can be used for fast planning, and illustrate the construction of an appropriate hierarchy for the Taxi domain. We used the above hierarchy to compute plans for three example queries, using dynamic programming and decision trees for planning and grounding classifiers, respectively. The results are given in Table 1; we next present each query, and step through the matching process in detail. |
| Researcher Affiliation | Academia | George Konidaris Departments of Computer Science and Electrical & Computer Engineering Duke University, Durham NC 27708 gdk@cs.duke.edu |
| Pseudocode | Yes | Algorithm 1: A simple hierarchical planning algorithm. |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code for the described methodology or links to a code repository. |
| Open Datasets | Yes | We now explain the construction and use of an abstraction hierarchy for a common hierarchical reinforcement learning benchmark: the Taxi domain [Dietterich, 2000], depicted in Figure 3a. |
| Dataset Splits | No | The paper describes the 'Taxi domain' but does not specify explicit training, validation, or test dataset splits for experiments. |
| Hardware Specification | Yes | All times are in milliseconds and are averaged over 100 samples, obtained using a Java implementation run on a Macbook Air with a 1.4 GHz Intel Core i5 and 8GB of RAM. |
| Software Dependencies | No | The paper mentions 'Java implementation' but does not provide specific version numbers for Java or any other software dependencies. |
| Experiment Setup | No | The paper describes the experiment using 'dynamic programming and decision trees' and defines the 'Taxi domain' setup, but it does not provide specific experimental setup details such as hyperparameters or training configurations (e.g., learning rate, batch size, number of epochs). |