{
  "fetched_at": "2026-10-22T09:35:10Z",
  "source_url": "https://www.kaggle.com/competitions/108-2-ntut-drl-hw1/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 homework uses OpenAI Gym as data source. \"rewards.csv\" is the example submission file. Please enter the averaged reward twice in both public and private field.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Learning Goal\n\nIn this homework, we choose \"FrozenLake8x8-v0\" as our learning environment. The goal of FrozenLake is to go from the starting state (S) to the goal state (G) by walking only on frozen tiles (F) and avoid holes (H). However, the ice is slippery, so you won't always move in the direction you intend (stochastic environment).\n\n### Observation\nType: Discrete (64)\n\nNum | Observation (State)\n---|---\n0 - 63 | For 8x8 square, counting each position from left to right, top to bottom\n\n### Actions\nType: Discrete(4)\n\nNum | Action\n--- | ---\n0 | Move Left\n1 | Move Down\n2 | Move Right\n3 | Move Up\n\n### Reward\nReward is 0 for every step taken, 0 for falling in the hole, 1 for reaching the final goal.\n\n### Starting State\nStarting state is at the top left corner.\n\n### Episode Termination\nReaching the goal or fall into one of the holes.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>\nIn this homework, you need to upload your averaged rewards after 1000 episodes. Because Kaggle requires at least two data rows, one for public and one for private data, you need to output the same score twice. An example \"rewards.csv\" is shown below:\n</p>\n \n<table>\n<tbody>\n<tr>\n<th>Id</th><th>Predicted</th>\n</tr>\n<tr>\n<td>FrozenLake8x8_public</td><td>0.312</td>\n</tr>\n<tr>\n<td>FrozenLake8x8_private</td><td>0.312</td>\n</tr>\n</tbody></table>\n\n<p>\nWe use Absolute Error (AE) as metric and set the target as 1. So if you get a score 0.312, you AE score will be 1 - 0.312 = 0.688. Lower AE means better model. The system will calculate the AE for you, so you should just update the averaged reward and don't reverse it.\n</p>\n<p></p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}