Arthur Charpentier on Nostr: Reinforcement learning (Q*), exploration / exploitation ...
Reinforcement learning (Q*), exploration / exploitation
Published at
2023-12-04 17:44:07Event JSON
{
"id": "0931b6896ccf2beb8b901bdac00a184e15fa3ece8a80fa45dd892f4db84c5d2f",
"pubkey": "3c989aa8626cfb78be01531a3cedee2f1e810325e00ab43911669d19e5b7a97e",
"created_at": 1701711847,
"kind": 1,
"tags": [
[
"proxy",
"https://mastodon.social/users/freakonometrics/statuses/111523387658292962",
"activitypub"
]
],
"content": "Reinforcement learning (Q*), exploration / exploitation\n\nhttps://files.mastodon.social/media_attachments/files/111/523/385/522/174/936/original/f739d5d07af32748.mp4",
"sig": "928fc13bd9af661c5bc7a3440f760a303849737b31faf582ebfb9c9eae42c8abdfe23f69fd3bd3b505331de84ea49fc5d8b9b204fb641ae8a4f9c2e13b7afdc5"
}
