benzogaga33 on Nostr: Reward Hacking in Reinforcement Learning
Published at
2024-12-19 15:10:02Event JSON
{
"id": "c14d971621f7bcaba37bf1676b25bbea2f9729b58435755abedee05f35e13975",
"pubkey": "b88242b313c3ec6c1675510a54c768a4a311cb0c8f5fa7859d2beb6b33614c87",
"created_at": 1734621002,
"kind": 1,
"tags": [
[
"proxy",
"https://mamot.fr/users/benzogaga33/statuses/113680122018213670",
"activitypub"
]
],
"content": "Reward Hacking in Reinforcement Learning https://lilianweng.github.io/posts/2024-11-28-reward-hacking/",
"sig": "b6b08267b74e934f88b6e97db7b6adb143fb4912f104af3b70c12320a03ecb3650e52b7f3d87555f7c4732dcb90fa5feb4a6e8642e351ba8df761acc7e1900d6"
}
