TD-GRPC: Temporal Difference Learning with Group Relative Policy Constraint for Humanoid Locomotion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nguyen, Khang, Nguyen, Khai, Le, An T., Peters, Jan, Huber, Manfred, Vien, Ngo Anh, Vu, Minh Nhat
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918025558491136
author Nguyen, Khang
Nguyen, Khai
Le, An T.
Peters, Jan
Huber, Manfred
Vien, Ngo Anh
Vu, Minh Nhat
author_facet Nguyen, Khang
Nguyen, Khai
Le, An T.
Peters, Jan
Huber, Manfred
Vien, Ngo Anh
Vu, Minh Nhat
contents Robot learning in high-dimensional control settings, such as humanoid locomotion, presents persistent challenges for reinforcement learning (RL) algorithms due to unstable dynamics, complex contact interactions, and sensitivity to distributional shifts during training. Model-based methods, \textit{e.g.}, Temporal-Difference Model Predictive Control (TD-MPC), have demonstrated promising results by combining short-horizon planning with value-based learning, enabling efficient solutions for basic locomotion tasks. However, these approaches remain ineffective in addressing policy mismatch and instability introduced by off-policy updates. Thus, in this work, we introduce Temporal-Difference Group Relative Policy Constraint (TD-GRPC), an extension of the TD-MPC framework that unifies Group Relative Policy Optimization (GRPO) with explicit Policy Constraints (PC). TD-GRPC applies a trust-region constraint in the latent policy space to maintain consistency between the planning priors and learned rollouts, while leveraging group-relative ranking to assess and preserve the physical feasibility of candidate trajectories. Unlike prior methods, TD-GRPC achieves robust motions without modifying the underlying planner, enabling flexible planning and policy learning. We validate our method across a locomotion task suite ranging from basic walking to highly dynamic movements on the 26-DoF Unitree H1-2 humanoid robot. Through simulation results, TD-GRPC demonstrates its improvements in stability and policy robustness with sampling efficiency while training for complex humanoid control tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13549
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TD-GRPC: Temporal Difference Learning with Group Relative Policy Constraint for Humanoid Locomotion
Nguyen, Khang
Nguyen, Khai
Le, An T.
Peters, Jan
Huber, Manfred
Vien, Ngo Anh
Vu, Minh Nhat
Robotics
Robot learning in high-dimensional control settings, such as humanoid locomotion, presents persistent challenges for reinforcement learning (RL) algorithms due to unstable dynamics, complex contact interactions, and sensitivity to distributional shifts during training. Model-based methods, \textit{e.g.}, Temporal-Difference Model Predictive Control (TD-MPC), have demonstrated promising results by combining short-horizon planning with value-based learning, enabling efficient solutions for basic locomotion tasks. However, these approaches remain ineffective in addressing policy mismatch and instability introduced by off-policy updates. Thus, in this work, we introduce Temporal-Difference Group Relative Policy Constraint (TD-GRPC), an extension of the TD-MPC framework that unifies Group Relative Policy Optimization (GRPO) with explicit Policy Constraints (PC). TD-GRPC applies a trust-region constraint in the latent policy space to maintain consistency between the planning priors and learned rollouts, while leveraging group-relative ranking to assess and preserve the physical feasibility of candidate trajectories. Unlike prior methods, TD-GRPC achieves robust motions without modifying the underlying planner, enabling flexible planning and policy learning. We validate our method across a locomotion task suite ranging from basic walking to highly dynamic movements on the 26-DoF Unitree H1-2 humanoid robot. Through simulation results, TD-GRPC demonstrates its improvements in stability and policy robustness with sampling efficiency while training for complex humanoid control tasks.
title TD-GRPC: Temporal Difference Learning with Group Relative Policy Constraint for Humanoid Locomotion
topic Robotics
url https://arxiv.org/abs/2505.13549