FADA is a three-stage Planner-IDM method that achieves few-shot domain adaptation for humanoid control by distilling an oracle policy then finetuning only the IDM on short target-domain rollouts via supervised learning.
Multi-embodiment locomotion at scale with extreme embodiment randomization
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.RO 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Trains embodiment-aware value functions on up to 50 robots and applies their gradients as differentiable surrogates to optimize held-out robot designs with over 1100 parameters.
A reinforcement learning method lets legged robots jointly learn information-seeking actions and predict joint-level and global embodiment parameters using a history-augmented URMA model in simulation.
citing papers explorer
-
FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control
FADA is a three-stage Planner-IDM method that achieves few-shot domain adaptation for humanoid control by distilling an oracle policy then finetuning only the IDM on short target-domain rollouts via supervised learning.
-
Shape Your Body: Value Gradients for Multi-Embodiment Robot Design
Trains embodiment-aware value functions on up to 50 robots and applies their gradients as differentiable surrogates to optimize held-out robot designs with over 1100 parameters.
-
Active Embodiment Identification with Reinforcement Learning for Legged Robots
A reinforcement learning method lets legged robots jointly learn information-seeking actions and predict joint-level and global embodiment parameters using a history-augmented URMA model in simulation.