cs.RONov 2, 2026

MAPO: Mixture of Experts with Alternating Policy Optimization for Universal Humanoid Motion Tracking

Authors: Seonghyeon Lim, Hyeonwoo Lee, Mincheol Kim, Kimin Lee, Hyun Myung

Organizations: School of Electrical Engineering, KAIST · Robotics Program, KAIST · Graduate School of AI, KAIST · Config

Abstract

Universal humanoid motion tracking is essential for enabling humanoid robots to perform diverse tasks in human environments. To capture the wide diversity of human motions, mixture-of-experts (MoE) policies have been widely adopted, leveraging dynamic routing to enhance policy expressiveness. However, we identify that divergence between old and updated policies can be misestimated during policy-gradient updates of MoE policies, due to their dynamic routing. Because most policy-gradient algorithms regulate policy updates based on the divergence, this misestimation can lead to either overly conservative or excessively large updates, which can yield a suboptimal policy. In this paper, we propose Mixture of Experts with Alternating Policy Optimization (MAPO), which alternately optimizes the router and the experts to avoid the divergence misestimation. MAPO consistently tracks 182 motions that PPO with MoE fails to track, whereas PPO with MoE tracks only one motion that MAPO fails to track. MAPO also attains the highest tracking success rate among the compared methods and the lowest tracking error across most error metrics, demonstrating its superior performance. Videos can be found on the project website: https://mapo-corl2026.github.io/MAPO/

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LooperMuscle: Fast and Stable Learning of Humanoid Whole-Body Tracking via Structured Mixture-of-Experts

    Aug 1, 2026Boyi Liu, Qijin Li, Tianqi Yu +2Robotic RLHumanoid Motion Tracking

  2. What Matters in Humanoid General Motion Tracking? An Empirical Study

    Jul 22, 2026Fabio Amadio, Enrico Mingo HoffmanHumanoid Robot ControlRobotic Policy Evaluation

  3. HoloMotion-1 Technical Report

    May 14, 2026Maiyue Chen, Kaihui Wang, Bo Zhang +7Robot Foundation ModelsImitation Learning