{ "fetched_at": "2026-10-22T09:24:41Z", "source_url": "https://www.kaggle.com/competitions/108-2-ntut-drl-hw2/data", "pages": [ { "name": "rules", "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "This competition uses OpenAI Gym CarRacing-v0 as data source. The file \"rewards.csv\" is the example submission file. Please enter the averaged reward of 10 runs twice in both public and private field.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "

In this homework, we are going to train an agent that can drive in CarRacing environment in OpenAI Gym. [link](https://gym.openai.com/envs/CarRacing-v0/)\nCarRacing is a top-down racing environment which consists of 96x96 pixels. Reward is -0.1 every frame and +1000/N for every track tile visited, where N is the total number of tiles in track. For example, if you have finished in 732 frames, your reward is 1000 - 0.1*732 = 926.8 points. Episode finishes when all tiles are visited. Some indicators shown at the bottom of the window and the state RGB buffer. From left to right: true speed, four ABS sensors, steering wheel position, gyroscope. CarRacing-v0 defines \"solving\" as getting average reward of 900 over 100 consecutive trials.\n

\n\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "

The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top (the page title appears above). For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have copied here:

\r\n
\r\n

The evaluation metric for this competition is Mean F1-Score. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:

\r\n

\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]

\r\n

The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.

\r\n

Submission Format

\r\n

For every author in the dataset, submission files should contain two columns: AuthorId and DuplicateAuthorIds. DuplicateAuthorIds should be a space-delimited list. Every AuthorId counts as his/her own duplicate, and every duplicate should be listed under each of its respective ids. For example, if you suspect author A, B, and C are the same, you should list (A,A B C), (B,B A C), (C,C A B).

\r\n

The file should contain a header and have the following format:

\r\n
AuthorId,DuplicateAuthorIds
1,1
8,8
9,9 10
10,10 9
etc.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }