RLPF uses reinforcement learning with a physics-simulator tracking reward and an alignment verification module to fine-tune a large text-to-motion model for physically feasible humanoid motions.
to implement an end-to-end training process, significantly improving the simulation and training speed of complex robotic tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control
RLPF uses reinforcement learning with a physics-simulator tracking reward and an alignment verification module to fine-tune a large text-to-motion model for physically feasible humanoid motions.