# SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending

arXiv: https://arxiv.org/abs/2506.09366 · HTML: https://mlsanity.com/paper/2506.09366/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 48 of its 54 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 48)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [The Option-Critic Architecture](https://mlsanity.com/paper/1609.05140/) (2016)
- [Learning robust perceptive locomotion for quadrupedal robots in the wild](https://mlsanity.com/paper/2201.08117/) (2022)
- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning](https://mlsanity.com/paper/2406.08858/) (2024)
- [HumanPlus: Humanoid Shadowing and Imitation from Humans](https://mlsanity.com/paper/2406.10454/) (2024)
- [Expressive Whole-Body Control for Humanoid Robots](https://mlsanity.com/paper/2402.16796/) (2024)
- [Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation](https://mlsanity.com/paper/2403.04436/) (2024)
- [ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills](https://mlsanity.com/paper/2502.01143/) (2025)
- [Universal Humanoid Motion Representations for Physics-Based Control](https://mlsanity.com/paper/2310.04582/) (2023)
- [HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation](https://mlsanity.com/paper/2403.10506/) (2024)
- [MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies](https://mlsanity.com/paper/1905.09808/) (2019)
- [TWIST: Teleoperated Whole-Body Imitation System](https://mlsanity.com/paper/2505.02833/) (2025)
- [Humanoid Parkour Learning](https://mlsanity.com/paper/2406.10759/) (2024)
- [HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots](https://mlsanity.com/paper/2410.21229/) (2024)
- [Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions](https://mlsanity.com/paper/2203.15103/) (2022)
- [ExBody2: Advanced Expressive Humanoid Whole-Body Control](https://mlsanity.com/paper/2412.13196/) (2024)
- [HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit](https://mlsanity.com/paper/2502.13013/) (2025)
- [Humanoid Locomotion as Next Token Prediction](https://mlsanity.com/paper/2402.19469/) (2024)
- [Multi-expert learning of adaptive legged locomotion](https://mlsanity.com/paper/2012.05810/) (2020)
- [OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models](https://mlsanity.com/paper/2402.10670/) (2024)
- [WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contacts](https://mlsanity.com/paper/2406.06005/) (2024)
- [Learning and Transfer of Modulated Locomotor Controllers](https://mlsanity.com/paper/1610.05182/) (2016)
- [RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation](https://mlsanity.com/paper/2407.04689/) (2024)
- [Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning](https://mlsanity.com/paper/2408.14472/) (2024)

## Built on by (most cited first, 9 of 9)

- [OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction](https://mlsanity.com/paper/2509.26633/) (2025)
- [Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulation](https://mlsanity.com/paper/2602.15828/) (2026)
- [CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation](https://mlsanity.com/paper/2606.23680/) (2026)
- [Learning Task-Agnostic Motifs to Capture the Continuous Nature of Animal Behavior](https://mlsanity.com/paper/2506.15190/) (2025)
- [CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives](https://mlsanity.com/paper/2512.14696/) (2025)
- [Self-Adaptive Learning and Model Predictive Control for Tracking Unknown Dynamics with No Regret](https://mlsanity.com/paper/2607.26370/) (2026)
- [LUCID: Latent-Skill Unified Control via Imagined Dynamics for Long-Horizon Humanoid Loco-Manipulation](https://mlsanity.com/paper/2608.07746/) (2026)
- [Skill Composition for Legged Robot Reinforcement Learning](https://mlsanity.com/paper/2609.14647/) (2026)
- [MASkillBlender: Decentralized Whole-Body Coordination for Multi-Humanoid Loco-Manipulation via Skill Blending](https://mlsanity.com/paper/2610.01102/) (2026)

## Abstract (arXiv)

Humanoid robots hold significant potential in accomplishing daily tasks across diverse environments thanks to their flexibility and human-like morphology. Recent works have made significant progress in humanoid whole-body control and loco-manipulation leveraging optimal control or reinforcement learning. However, these methods require tedious task-specific tuning for each task to achieve satisfactory behaviors, limiting their versatility and scalability to diverse tasks in daily scenarios. To that end, we introduce SkillBlender, a novel hierarchical reinforcement learning framework for versatile humanoid loco-manipulation. SkillBlender first pretrains goal-conditioned task-agnostic primitive skills, and then dynamically blends these skills to accomplish complex loco-manipulation tasks with minimal task-specific reward engineering. We also introduce SkillBench, a parallel, cross-embodiment, and diverse simulated benchmark containing three embodiments, four primitive skills, and eight challenging loco-manipulation tasks, accompanied by a set of scientific evaluation metrics balancing accuracy and feasibility. Extensive simulated experiments show that our method significantly outperforms all baselines, while naturally regularizing behaviors to avoid reward hacking, resulting in more accurate and feasible movements for diverse loco-manipulation tasks in our daily scenarios. Our code and benchmark will be open-sourced to the community to facilitate future research. Project page: https://usc-gvl.github.io/SkillBlender-web/.