Precise Manipulation with Efficient Online RL

We extract an RL Token from VLA models to enable fast online RL and improve throughput on precise tasks with few hours of data.

Precise Manipulation with Efficient Online RL Precise Manipulation with Efficient Online RL Published March 19, 2026 Email research@physicalintelligence.company Charles Xu, Jost Tobias Springenberg, Michael Equi, Ali Amin, Adnan Esmail, Sergey Levine, Liyiming Ke Paper RLT .pdf Loading… Our models can follow diverse instructions and perform a wide range of tasks, from folding laundry and making coffee to cooking a grilled cheese sandwich . But for many applications, broad competence is not enough: the hardest parts of physical tasks require precision, dexterity, and speed. Picking up a screwdr

saved by

• Information Flow
• Vincent Huang
• KRUPAL VIRANI
• Anya Singh
• Alex K

related reading

• 45d74e190008c7bff2845ffc8e3facd3-Paper-Conference.pdfproceedings.iclr.cc
• pistar06.pdfpi.website
• e5b5c402bb7bd5e60bede6961d6fe39e-Paper-Conference.pdfproceedings.iclr.cc
• A VLA that Learns from Experiencepi.website
• FASTERinnovator-zero.github.io
• You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectoriesarxiv.org
• π*0.6: a VLA That Learns From Experiencephysicalintelligence.company
• A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulationtoyotaresearchinstitute.github.io
• State of Robot Learning, December 2025vedder.io
• A VLA with Open-World Generalizationpi.website
• Causal Video Models Are Data-Efficient Robot Policy Learners | Rhoda AIrhoda.ai
• [2509.22407] EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transferarxiv.org