Event JSON
{
"id": "1f44c19812ea5d29be6eef2101fee997b2125d3365615ade1008f6914eb9458f",
"pubkey": "95ea081a627cee44e532825986ecc662139d068c4bdacbe820a8f445b9c6c06b",
"created_at": 1720260700,
"kind": 1,
"tags": [
[
"p",
"95ea081a627cee44e532825986ecc662139d068c4bdacbe820a8f445b9c6c06b"
],
[
"e",
"6a8f08b36693c621a793338bdec8ceda0133408488ac53de6eb79322c855c96e",
"",
"reply"
],
[
"proxy",
"https://recsys.social/@brohrer/112739005287098154",
"web"
],
[
"e",
"800ba7c73cf73dcf9bf7ebdf59e84f0664cbb253f261e0e0108fd128be4e3937",
"",
"root"
],
[
"t",
"reinforcementlearning"
],
[
"proxy",
"https://recsys.social/users/brohrer/statuses/112739005287098154",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://recsys.social/users/brohrer/statuses/112739005287098154",
"pink.momostr"
],
[
"expiration",
"1722852703"
]
],
"content": "This is unusually good performance for Q-learning. I juiced it up with my own home rolled curiosity-driven experimentation approach. I haven’t written it up yet, but the code is here. \n#ReinforcementLearning\n\nhttps://codeberg.org/brohrer/myrtle/src/branch/main/src/myrtle/agents/q_learning_curiosity.py",
"sig": "5cae7cfe7cce6264be1bc5951d3007812e32223ea03e55378255036fc5bf9b059e5e1b170e67bf4232826a74ff4545b45547fbc9861ee6e1f16d4c00f9c783c2"
}