Side project update on Myrtle, a real time reinforcement learning workbench.
I have a classic algorithm (Q-Learning) learning a classic task (getting a simulated pendulum to balance pointing upward).
When it’s just starting out, it’s just a flailing pendulum, depicted in this console animation.
Brandon Rohrer /
npub1jh…9eag0
2024-07-06 09:46:21
Author Public Key
npub1jh4qsxnz0nhyfefjsfvcdmxxvgfe6p5vf0dvh6pq4r6ytwwxcp4sl9eag0Published at
2024-07-06 09:46:21Event JSON
{
"id": "800ba7c73cf73dcf9bf7ebdf59e84f0664cbb253f261e0e0108fd128be4e3937",
"pubkey": "95ea081a627cee44e532825986ecc662139d068c4bdacbe820a8f445b9c6c06b",
"created_at": 1720259181,
"kind": 1,
"tags": [
[
"proxy",
"https://recsys.social/@brohrer/112738905749051334",
"web"
],
[
"imeta",
"url https://cdn.masto.host/recsyssocial/media_attachments/files/112/738/905/064/268/128/original/bc14d9465426e5f4.mp4",
"m video/mp4"
],
[
"proxy",
"https://recsys.social/users/brohrer/statuses/112738905749051334",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://recsys.social/users/brohrer/statuses/112738905749051334",
"pink.momostr"
],
[
"expiration",
"1722851185"
]
],
"content": "Side project update on Myrtle, a real time reinforcement learning workbench.\n\nI have a classic algorithm (Q-Learning) learning a classic task (getting a simulated pendulum to balance pointing upward).\n\nWhen it’s just starting out, it’s just a flailing pendulum, depicted in this console animation.\nhttps://cdn.masto.host/recsyssocial/media_attachments/files/112/738/905/064/268/128/original/bc14d9465426e5f4.mp4\n",
"sig": "32285513c9d4c6146c6b33b96531d480b26e242aef22e0f7235669140c2fbe77b6dc9dc225b50f10527f2f227a15c4fbc8d2556c893b2ad7c1da11f7df0b5f1d"
}