QTOP: Scaling Humanoid Motion Tracking with Quantile Critics

Learning human motion tracking policies through reinforcement learning (RL) has emerged as a core capability that underpins a majority of recent progress in humanoid whole-body control. However, achieving generalization to unseen motions at high fidelity requires jointly scaling training to thousands of GPU and dataset hours. This work hypothesizes that motion tracking is inherently compute-bound because training on a diverse set of motions introduces learning interference, similar to multi-task RL. To tackle this, we propose Quantile Tracking Optimization (QTOP), which improves sample efficiency by introducing a distributional advantage estimate conditioned on state and reference pairs. QTOP outperforms on and off-policy RL baselines both in simulation and real-world tracking scenarios on multiple datasets by up to 10\%. Furthermore, we establish a scaling law for QTOP and find that, aside from scaling predictably, dataset size has minimal impact on performance for moderately sized GPU hour regimes.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.20791
Primary Topic
Reinforcement Learning in Robotics
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

QTOP: Scaling Humanoid Motion Tracking with Quantile Critics

Daniel Dijkman, Dana Kianfar, Markus Peschl
arXiv (Cornell University)
Reinforcement Learning in Robotics
preprint

QTOP: Scaling Humanoid Motion Tracking with Quantile Critics

Daniel Dijkman, Dana Kianfar, Markus Peschl
preprint en

Abstract

Learning human motion tracking policies through reinforcement learning (RL) has emerged as a core capability that underpins a majority of recent progress in humanoid whole-body control. However, achieving generalization to unseen motions at high fidelity requires jointly scaling training to thousands of GPU and dataset hours. This work hypothesizes that motion tracking is inherently compute-bound because training on a diverse set of motions introduces learning interference, similar to multi-task RL. To tackle this, we propose Quantile Tracking Optimization (QTOP), which improves sample efficiency by introducing a distributional advantage estimate conditioned on state and reference pairs. QTOP outperforms on and off-policy RL baselines both in simulation and real-world tracking scenarios on multiple datasets by up to 10\%. Furthermore, we establish a scaling law for QTOP and find that, aside from scaling predictably, dataset size has minimal impact on performance for moderately sized GPU hour regimes.

arXiv (Cornell University)
Reinforcement Learning in Robotics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon