// COMPANY
RLBench
SECTOR ROBOTICSMENTIONS 3LAST SEEN AUGUST 4, 2026
// OVERVIEW
Widely-used robotics benchmark environment for evaluating manipulation policies.
// RECENT MENTIONS
// SIGNALS
3 SIGNALS
01
product·arXiv Physical AI·AUGUST 4, 2026
“Serves as the original basis for the 3D manipulation tasks used in the paper”
Source→02
mention·arXiv Physical AI·AUGUST 4, 2026
“training time for a manipulation task was reduced from 7 hours and 54 minutes (in RLBench) to just 27 minutes”
Source→03
mention·arXiv Physical AI·JUNE 1, 2026
“In simulation (RoboTwin, RLBench), the framework delivers up to a 207% relative improvement.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.