Joint velocity action space outperforms pose increment, pose velocity, and joint position increment for smoothness and performance in sim-to-real vision-based manipulation.
A comparison of action spaces for learning manipulation tasks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation
Joint velocity action space outperforms pose increment, pose velocity, and joint position increment for smoothness and performance in sim-to-real vision-based manipulation.