{
  "id": 306803,
  "title": "Reinforcement learning vs Supervised",
  "url": "/competitions/h-and-m-personalized-fashion-recommendations/discussion/306803",
  "author_name": "",
  "post_date": "2022-02-11T02:46:44.327834800Z",
  "votes": 3,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hi Kagglers,</p>\n<p>I would like to know if you think it's a good idea to go for reinforcement learning like contextual bandits? Or a supervised approach is enough for this problem.</p>\n<p>Thank you!</p>",
  "messages": [
    {
      "id": "1685069",
      "postDate": "02/11/2022 02:46:44",
      "content": "<p>Hi Kagglers,</p>\n<p>I would like to know if you think it's a good idea to go for reinforcement learning like contextual bandits? Or a supervised approach is enough for this problem.</p>\n<p>Thank you!</p>",
      "rawMarkdown": "Hi Kagglers,\n\nI would like to know if you think it's a good idea to go for reinforcement learning like contextual bandits? Or a supervised approach is enough for this problem.\n\nThank you!",
      "votes": null
    },
    {
      "id": "1685720",
      "postDate": "02/11/2022 13:56:07",
      "content": "<p>Nice idea!</p>",
      "rawMarkdown": "Nice idea!",
      "votes": null
    },
    {
      "id": "1707768",
      "postDate": "02/28/2022 18:50:25",
      "content": "<p>I'm evaluating whether I can resolve this problem with Deep RL.  DRL for recommend system is a pretty cool idea. </p>",
      "rawMarkdown": "I'm evaluating whether I can resolve this problem with Deep RL.  DRL for recommend system is a pretty cool idea.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1685720,
      "author_name": "kotaronoguchi",
      "author_url": "",
      "post_date": "02/11/2022 13:56:07",
      "content": "<p>Nice idea!</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1707768,
      "author_name": "guomaobin",
      "author_url": "",
      "post_date": "02/28/2022 18:50:25",
      "content": "<p>I'm evaluating whether I can resolve this problem with Deep RL.  DRL for recommend system is a pretty cool idea. </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1685069": "Hi Kagglers,\n\nI would like to know if you think it's a good idea to go for reinforcement learning like contextual bandits? Or a supervised approach is enough for this problem.\n\nThank you!",
    "1685720": "Nice idea!",
    "1707768": "I'm evaluating whether I can resolve this problem with Deep RL.  DRL for recommend system is a pretty cool idea."
  },
  "source": "meta"
}