← Back to Benchmarks
simmediumpolicy-learningmetric · varies
MorFiC: Fixing Value Miscalibration for Zero-Shot Quadruped Transfer
Description
Generalizing learned locomotion policies across quadrupedal robots with different morphologies remain a challenge. Policies trained on a single robot often break when deployed on embodiments with different mass distributions, kinematics, joint limits, or actuation constraints, forcing per robot retraining. We present MorFiC, a reinforcement learning approach for zero-shot cross-morphology locomotion using a single shared policy. MorFiC resolves a key failure mode in multi-morphology actor-critic