Chelsea Finn
2 things Chelsea uses or recommends, from 1 episode.
Chelsea's top picks
What Chelsea uses or recommends most, ranked by how often and how strongly. Ad reads don't count.
Uses and recommends it · 1 episode
"We see a drastic increase in success rate and throughput — specifically around a 2x throughput just from the RL stage itself, showing how we can get much greater reliability from reinforcement learning. For the espresso task, we achieved a 90% or over 90% success rate."
Recommends it · 1 episode
"The PI zero and PI05 models are open source. We've seen a lot of people get a lot of use out of those models already. Even right off the bat, I think you can use them — just taking PI05 or your favorite model and fine-tuning it is the way to go."
All 2 of Chelsea's picks
- Reinforcement Learning Uses and recommends it "We see a drastic increase in success rate and throughput — specifically around a 2x throughput just from the RL stage itself, showing how we can get much greater reliability from reinforcement learning. For the espresso task, we achieved a 90% or over 90% success rate." +1 other
- pi0 Recommends it "The PI zero and PI05 models are open source. We've seen a lot of people get a lot of use out of those models already. Even right off the bat, I think you can use them — just taking PI05 or your favorite model and fine-tuning it is the way to go." Only Chelsea