# Exploiting Hierarchical Controller Structure in Contextual Parameter Learning for Humanoid Loco-Manipulation

arXiv: https://arxiv.org/abs/2610.04609 · HTML: https://mlsanity.com/paper/2610.04609/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 3 Oct 2026.

## Builds on (most cited first, 15 of 15)

- [Bayesian Optimization of Composite Functions](https://mlsanity.com/paper/1906.01537/) (2019)
- [Tuning Legged Locomotion Controllers via Safe Bayesian Optimization](https://mlsanity.com/paper/2306.07092/) (2023)
- [Performance-Driven Cascade Controller Tuning with Bayesian Optimization](https://mlsanity.com/paper/2007.12536/) (2020)
- [Performance-based Trajectory Optimization for Path Following Control Using Bayesian Optimization](https://mlsanity.com/paper/2103.15416/) (2021)
- [Momentum Control with Hierarchical Inverse Dynamics on a Torque-Controlled Humanoid](https://mlsanity.com/paper/1410.7284/) (2014)
- [Contextual Tuning of Model Predictive Control for Autonomous Racing](https://mlsanity.com/paper/2110.02710/) (2021)
- [Safe and Stable Closed-Loop Learning for Neural-Network-Supported Model Predictive Control](https://mlsanity.com/paper/2409.10171/) (2024)
- [Violation-Aware Contextual Bayesian Optimization for Controller Performance Optimization with Unmodeled Constraints](https://mlsanity.com/paper/2301.12099/) (2023)
- [Safe Hierarchical Model Predictive Control and Planning for Autonomous Systems](https://mlsanity.com/paper/2203.14269/) (2022)
- [Controller Adaptation via Learning Solutions of Contextual Bayesian Optimization](https://mlsanity.com/paper/2403.04881/) (2024)
- [BOIS: Bayesian Optimization of Interconnected Systems](https://mlsanity.com/paper/2311.11254/) (2023)
- [Robust Humanoid Locomotion Using Trajectory Optimization and Sample-Efficient Learning](https://mlsanity.com/paper/1907.04616/) (2019)
- [Time-Series-Informed Closed-loop Learning for Sequential Decision Making and Control](https://mlsanity.com/paper/2412.02423/) (2024)
- [A Hierarchical Surrogate Model for Efficient Multi-Task Parameter Learning in Closed-Loop Control](https://mlsanity.com/paper/2508.12738/) (2025)
- [Efficient Controller Learning from Human Preferences and Numerical Data Via Multi-Modal Surrogate Models](https://mlsanity.com/paper/2603.24138/) (2026)

## Abstract (arXiv)

Hierarchical control architectures are widely used to decompose complex control problems into interacting control levels and are particularly important in robotics, where planning, whole-body motion, and lower-level control must be coordinated across different levels of abstraction and time scales. Their overall closed-loop performance, however, depends strongly on parameters distributed across the hierarchy, such that tuning controllers on different levels independently may neglect relevant cross-layer interactions. We propose a contextual Bayesian optimization framework for joint parameter learning in hierarchical control systems. Rather than modeling closed-loop performance only as a scalar black-box function, we retain separate observations of task performance, realization quality, and control effort. A correlated multi-output Gaussian process models these performance components, while their known aggregation into the overall closed-loop objective is evaluated analytically. The formulation exploits three complementary consequences of hierarchical control: informative performance quantities exposed by the hierarchy, coupling between parameters of different controller levels, and variations of these relations with operating conditions. We evaluate the approach for humanoid loco-manipulation, jointly tuning a centroidal predictive controller and a whole-body controller for physical box pushing under varying box mass. The proposed method achieves the lowest mean empirical regret during both training and adaptation among the considered baselines.