# STRIDE: Learning Humanoid Locomotion in Minutes with Acceleration-Based Rewards

DevFeed: [STRIDE: Learning Humanoid Locomotion in Minutes with Acceleration-Based Rewards](<https://devfeed.tech/articles/stride-learning-humanoid-locomotion-in-minutes-with-acceleration-based-rewards-123316.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.08857>)

Author: Nico Bohlinger, Jan Peters

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>)

Tags: [acceleration](<https://devfeed.tech/tags/acceleration.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [falls](<https://devfeed.tech/tags/falls.md>), [g1](<https://devfeed.tech/tags/g1.md>), [gap](<https://devfeed.tech/tags/gap.md>), [humanoid](<https://devfeed.tech/tags/humanoid.md>), [imu](<https://devfeed.tech/tags/imu.md>), [learning](<https://devfeed.tech/tags/learning.md>), [minutes](<https://devfeed.tech/tags/minutes.md>), [motion-capture](<https://devfeed.tech/tags/motion-capture.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [reward](<https://devfeed.tech/tags/reward.md>), [rl](<https://devfeed.tech/tags/rl.md>), [robot](<https://devfeed.tech/tags/robot.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [symmetry](<https://devfeed.tech/tags/symmetry.md>), [training](<https://devfeed.tech/tags/training.md>)

## AI overview

STRIDE trains humanoid locomotion using a reward based on following commanded acceleration, which requires only an onboard IMU rather than base-velocity measurements from motion capture or a well-calibrated state estimator. The method combines off-policy RL algorithm XQC with high-gain joint position control and left-right symmetry augmentation. In simulation, it learned to walk on Unitree G1 and Booster T1 robots within 14 minutes of samples. With the two added components, training falls decreased by 81%; without them, learning took over an hour. The supplied text is an abstract and does not establish results on physical robots.

## Source excerpt

arXiv:2611.08857v1 Announce Type: cross Abstract: Learning locomotion directly on a humanoid robot is a promising direction to avoid the sim-to-real gap. However, locomotion rewards in Reinforcement Learning (RL) typically track the base velocity, which cannot be measured onboard without an external motion capture system or well-calibrated state estimator. This is why we introduce \method{}, which learns humanoid locomotion from minutes of samples with a reward that only requires the onboard Inertial Measurement Unit (IMU). Instead of tracking the base velocity, STRIDE rewards the robot for following a commanded acceleration profile. To learn efficiently from this reward, we use the off-policy RL algorithm XQC and combine a high gain setting for the joint position controllers with left-right symmetry augmentation. In simulation, STRIDE learns to walk on the Unitree G1 and Booster T1 humanoids within 14 minutes of samples. Compared to learning without these two components, it reduces the falls during training by 81%, while without them the robot learns only in over an hour.