
Max Sobol Mark
@maxsobolmark
PhD student at @CarnegieMellon
ID: 2202153178
https://maxsobolmark.com 30-11-2013 19:19:01
55 Tweet
145 Followers
123 Following


How can we fine-tune generalist policies autonomously w/ RL (value functions)? Max Sobol Mark's new paper on Policy-agnostic RL provides a single way to fine-tune generalist VLAs w/ any backbone, output, size (we fine-tune 7B OpenVLA on real robot) policyagnosticrl.github.io🧵⬇️









Felicitamos a todo el equipo de TEDxORTArg y sobre todo a 3 oradores de lujo @SantiAranguri, @Joelmax36 y @bilinkisn por #TEDxORTArg2014!



I vote for Creactivis to #UpgradeYourWorld #Vote windows.com/upgradeyourwor…