A thing I learned about synchronization in real-time reinforcement learning
Synchronization between agents in worlds gets trickier when the world is operating in real time, as with robots and other physical systems. In non real-time RL, the world can wait for the agent to plan its next action. It is a turn-taking scenario where the agent waits for the world to make its next move and vice versa. But for physical hardware, the world doesn't wait for the agent to compute.
1/
Brandon Rohrer /
npub1jh…9eag0
2024-06-25 13:29:36
Author Public Key
npub1jh4qsxnz0nhyfefjsfvcdmxxvgfe6p5vf0dvh6pq4r6ytwwxcp4sl9eag0Published at
2024-06-25 13:29:36Event JSON
{
"id": "b03e3cda634a9754d134afe09a048ceefb4264e09db66375b3b95d8ac4750fc6",
"pubkey": "95ea081a627cee44e532825986ecc662139d068c4bdacbe820a8f445b9c6c06b",
"created_at": 1719322176,
"kind": 1,
"tags": [
[
"proxy",
"https://recsys.social/@brohrer/112677498128884866",
"web"
],
[
"proxy",
"https://recsys.social/users/brohrer/statuses/112677498128884866",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://recsys.social/users/brohrer/statuses/112677498128884866",
"pink.momostr"
],
[
"expiration",
"1721914180"
]
],
"content": "A thing I learned about synchronization in real-time reinforcement learning\n\nSynchronization between agents in worlds gets trickier when the world is operating in real time, as with robots and other physical systems. In non real-time RL, the world can wait for the agent to plan its next action. It is a turn-taking scenario where the agent waits for the world to make its next move and vice versa. But for physical hardware, the world doesn't wait for the agent to compute. \n\n1/",
"sig": "163ad229b25aa968a4bc2112ad2acf950dfb8e615882c5c12a3a919e378f11622d0e43269543182f5fb3648d694044ec1ca4c3f3297ca3a5fc9075d81e4197a6"
}