AGILE: A Comprehensive Workflow for Humanoid Loco-Manipulation Learning

TL;DR

AGILE is an end-to-end workflow that standardizes the development, evaluation, and deployment of humanoid reinforcement learning policies, significantly improving transfer reliability from simulation to real robots.

Contribution

The paper introduces AGILE, a comprehensive, standardized pipeline for humanoid RL that enhances robustness, reproducibility, and sim-to-real transfer through systematic stages and diagnostics.

Findings

Successful transfer of five humanoid skills to real robots

Enhanced robustness and reproducibility in humanoid RL workflows

Automated regression testing and evaluation diagnostics implemented

Abstract

Recent advances in reinforcement learning (RL) have enabled impressive humanoid behaviors in simulation, yet transferring these results to new robots remains challenging. In many real deployments, the primary bottleneck is no longer simulation throughput or algorithm design, but the absence of systematic infrastructure that links environment verification, training, evaluation, and deployment in a coherent loop. To address this gap, we present AGILE, an end-to-end workflow for humanoid RL that standardizes the policy-development lifecycle to mitigate common sim-to-real failure modes. AGILE comprises four stages: (1) interactive environment verification, (2) reproducible training, (3) unified evaluation, and (4) descriptor-driven deployment via robot/task configuration descriptors. For evaluation stage, AGILE supports both scenario-based tests and randomized rollouts under a shared suite of motion-quality diagnostics, enabling automated regression testing and principled robustness assessment. AGILE also incorporates a set of training stabilizations and algorithmic enhancements in training stage to improve optimization stability and sim-to-real transfer. With this pipeline in place, we validate AGILE across five representative humanoid skills spanning locomotion, recovery, motion imitation, and loco-manipulation on two hardware platforms (Unitree G1 and Booster T1), achieving consistent sim-to-real transfer. Overall, AGILE shows that a standardized, end-to-end workflow can substantially improve the reliability and reproducibility of humanoid RL development.