{
 "entities": {
  "M146400": {
   "pageid": 71187427,
   "ns": 0,
   "title": "M146400",
   "lastrevid": 1179435070,
   "modified": "2026-10-25T09:24:03Z",
   "type": "item",
   "id": "M146400",
   "labels": {
    "en": {
     "language": "en",
     "value": "Reinforcement learning from human feedback"
    }
   },
   "descriptions": {
    "en": {
     "language": "en",
     "value": "Training a model with a reward learned from human judgments"
    }
   },
   "aliases": {},
   "claims": {},
   "sitelinks": {
    "molecupedia": {
     "site": "molecupedia",
     "title": "Reinforcement learning from human feedback",
     "badges": [],
     "url": "https://molecularreality.com/wiki/Reinforcement_learning_from_human_feedback"
    }
   },
   "_note": "Moleculedata is a parody of a structured-data wiki. Values are copied from the article infobox."
  }
 }
}