In this assignment, you are challenged to analyze and compare solutions of a problem, game, algorithm, model, or anything else that can be represented by sequential states. For this, you will project the high-dimensional states to the two-dimensional space, connect the states, and add meta-data to the visualization.
Exemplary solutions are provided in the solution_rubik.ipynb and solution_2048.ipynb notebooks.
Further examples to analyze are (board) games and approximation algorithms. The 2048 notebook uses OpenAI Gym to create a game environment and produce state data. There is a variety of first and third party environments for Gym that can be used.
For the intermediate submission, please enter the group and dataset information. Coding is not yet necessary.
Team Name: [TODO]
Group Members
| Student ID | First Name | Last Name | |
|---|---|---|---|
| [TODO] | [TODO] | [TODO] | |
| [TODO] | [TODO] | [TODO] | |
| [TODO] | [TODO] | [TODO] | |
| [TODO] | [TODO] | [TODO] |
Please add your dataset to the repository (or provide a link if it is too large) and answer the following questions about it:
- Which dataset are you using? What is it about?
- Where did you get this dataset from (i.e., source of the dataset)? How was the dataset generated?
- What is dataset size in terms of nodes, items, rows, columns, ...?
- What do you want to analyze?
- What are you expecting to see?
[TODO]
- Make sure that you pushed your GitHub repository and not just committed it locally.
- Sending us an email with the code is not necessary.
- Update the environment.yml file if you need additional libraries, otherwise the code is not executeable.
- Save your final executed notebook(s) as html (File > Download as > HTML) and add them to your repository.
Checkout this repo and change into the folder:
git clone https://github.com/jku-icg-classroom/xai_proj_space_2020-<GROUP_NAME>.git
cd xai_proj_space_2020-<GROUP_NAME>
Load the conda environment from the shared environment.yml file:
conda env create -f environment.yml
conda activate xai_proj_space
Hint: For more information on Anaconda and enviroments take a look at the README in our tutorial repository.
Then launch Jupyter Lab:
jupyter lab
Go to http://localhost:8888/ and open the template notebook.
Alternatively, you can also work with binder.