Max Sobol Mark

@maxsobolmark

Pinned
Max Sobol Mark
@maxsobolmark
Feb 19
Excited to share Big Picture Policies (BPP), from my internship at Google DeepMind! 🤖 Many tasks we expect robots to do need memory, but the best policies today are memoryless. We study how to fix this, unlocking long-horizon searching behaviors and solving 6-step tasks. 🧵👇
00:00
5
Max Sobol Mark
@maxsobolmark
Apr 25, 2025
I'll be presenting Policy-Agnostic RL: Fine-Tuning of Any Policy Class and Backbone at the Robot Learning (Sunday) and GenBot (Monday) workshops as Orals at #ICLR2025! Happy to chat or meet!
Max Sobol Mark
@maxsobolmark
Dec 16, 2024
Robotics foundation models struggle with new tasks. Can a single RL method efficiently improve any policy, including large generalists (7B OpenVLA) and diffusion policies, in the real world? Our new paper PA-RL does just that! PolicyAgnosticRL.github.io arxiv.org/abs/2412.06685 🧵👇
00:00
Max Sobol Mark
@maxsobolmark
Dec 16, 2024
Robotics foundation models struggle with new tasks. Can a single RL method efficiently improve any policy, including large generalists (7B OpenVLA) and diffusion policies, in the real world? Our new paper PA-RL does just that! PolicyAgnosticRL.github.io arxiv.org/abs/2412.06685 🧵👇
00:00
2
Max Sobol Mark
@maxsobolmark
Jul 29, 2015
I vote for @creactivis to #UpgradeYourWorld #Vote windows.com/upgradeyourwor…
Max Sobol Mark
@maxsobolmark
Oct 29, 2014
Increíble experiencia #TEDxORTArg2014