TwinRL expands RL exploration via digital twin reconstruction and twin RL warm-up to guide real-world learning, reaching near-100% success with 20 minutes of on-robot time across four tasks.
Robomamba: Effi- cient vision-language-action model for robotic reasoning and manipulation.Advances in Neural Information Processing Systems, 37:40085–40110
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
-
TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation
TwinRL expands RL exploration via digital twin reconstruction and twin RL warm-up to guide real-world learning, reaching near-100% success with 20 minutes of on-robot time across four tasks.