Nirvana Robotics retweeted
A robot policy that works 50% of the time is a demo. Getting it to 99% is the whole game.
So I made an interactive course on the SOTA RL techniques people use to close that gap, plus a map of 952 papers and posts. Updated weekly.
github.com/afinitus/awesome-…
afinitus.github.io/awesome-h…
Nirvana Robotics retweeted
Beyond these scaling law results, Dyna-2 has many new capabilities that exceed our prior models. First, it has excellent language following capabilities through both scaling data and choosing the right world-modeling objective; it’s the first internal model that clears our internal language following benchmark.
📢 We're #hiring a Robotics Research Scientist in NYC;
Build safe humanoids for real manufacturing. Work on World Models, Visual Language Action Models, Deep Reinforcement Learning and deploy on real robots.
Apply on our website below ⤵️
nrvana.ai/robotics-research-…




