Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents
Paper
•
2507.23698
•
Published
•
10
ROCKET
ROCKET is the research series that explores vision-based goal specification methods.
Note This is ROCKET-3!
-
ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment
Paper • 2503.02505 • Published • 7 -
ROCKET-1: Master Open-World Interaction with Visual-Temporal Context Prompting
Paper • 2410.17856 • Published • 52 -
phython96/ROCKET-1
Robotics • Updated • 13 • 5 -
phython96/ROCKET-2-1x-22w
Updated • 84 -
phython96/ROCKET-2-1.5x-17w
Updated • 37 -
CraftJarvis/minestudio-data-10xx-v110
Updated • 120 -
CraftJarvis/minestudio-data-9xx-v110
Updated • 99 -
CraftJarvis/minestudio-data-8xx-v110
Updated • 113 -
CraftJarvis/minestudio-data-7xx-v110
Updated • 279 -
CraftJarvis/minestudio-data-6xx-v110
Updated • 134 -
CraftJarvis/MineStudio_ROCKET-1.12w_EMA
Updated • 19