stijn.bsky.social
Mid/post-training, RL, synth data & domain-specific models Pioneered (Nov '24) practical multi-Agent coding: https://git.new/WPTggu6 ⛰ ⛷️
👤 Joined on 27 June 2023
Followers
Following
Total Posts
@stijn.bsky.social@stijn.bsky.social → @agenticsolutions.nl@agenticsolutions.nl → @stijn.bsky.socialWhat if you could train agents on a 𝗱𝗲𝗰𝗮𝗱𝗲 of driving experience in 𝘂𝗻𝗱𝗲𝗿 𝗮𝗻 𝗵𝗼𝘂𝗿, on a single GPU? Excited to share 𝙋𝙪𝙛𝙛𝙚𝙧𝘿𝙧𝙞𝙫𝙚 2.0: A fast, friendly driving simulator with RL training via PufferLib at 𝟯𝟬𝟬𝗞 𝘀𝘁𝗲𝗽𝘀/𝘀𝗲𝗰 🐡 + 🚗 youtu.be/LfQ324R-cbE?...
Show Posttailwind + motion + ☀️ #designsky
Show PostGPUDrive got accepted to ICLR 2025! With that, we release GPUDrive v0.4.0! 🚨 You can now install the repo and run your first fast PPO experiment in under 10 minutes. I’m honestly so excited about the new opportunities and research the sim makes possible. 🚀 1/2
Show Post