REVIEW 4 cited by
MoE-Loco: Mixture of Experts for Multitask Locomotion
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We present MoE-Loco, a Mixture of Experts (MoE) framework for multitask locomotion for legged robots. Our method enables a single policy to handle diverse terrains, including bars, pits, stairs, slopes, and baffles, while supporting quadrupedal and bipedal gaits. Using MoE, we mitigate the gradient conflicts that typically arise in multitask reinforcement learning, improving both training efficiency and performance. Our experiments demonstrate that different experts naturally specialize in distinct locomotion behaviors, which can be leveraged for task migration and skill composition. We further validate our approach in both simulation and real-world deployment, showcasing its robustness and adaptability.
Forward citations
Cited by 4 Pith papers
-
Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning
A lifelong robot learning method that mixes a growing library of LoRA-style experts with a context router and replays router coefficients to achieve forward transfer with near-zero forgetting.
-
Self-Adaptive Learning and Model Predictive Control for Tracking Unknown Dynamics with No Regret
A self-adaptive MPC with multiple online-learned RFF predictors and Hedge-based selection achieves O(T^{3/4}) expected regret for tracking unknown, switching target dynamics.
-
FARM: Frame-Accelerated Augmentation and Residual Mixture-of-Experts for Physics-Based High-Dynamic Humanoid Control
FARM combines frame-accelerated augmentation with a residual mixture-of-experts to track high-dynamic humanoid motions, cutting tracking failures by 42.8% on a new HDHM benchmark.
-
GMT: General Motion Tracking for Humanoid Whole-Body Control
GMT trains a single unified humanoid policy using adaptive sampling and mixture-of-experts, achieving lower tracking errors than a re-implemented ExBody2 across diverse whole-body motions.
Discussion (0). Continue with ORCID to comment.