# Embodied Learning of Reward for Musculoskeletal Control with Vision Language Models

arXiv: https://arxiv.org/abs/2512.23077 · HTML: https://mlsanity.com/paper/2512.23077/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 28 Dec 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 24 of 24)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Language to Rewards for Robotic Skill Synthesis](https://mlsanity.com/paper/2306.08647/) (2023)
- [Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning](https://mlsanity.com/paper/2310.12921/) (2023)
- [RoboCLIP: One Demonstration is Enough to Learn Robot Policies](https://mlsanity.com/paper/2310.07899/) (2023)
- [Using Natural Language for Reward Shaping in Reinforcement Learning](https://mlsanity.com/paper/1903.02020/) (2019)
- [DrEureka: Language Model Guided Sim-To-Real Transfer](https://mlsanity.com/paper/2406.01967/) (2024)
- [MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control](https://mlsanity.com/paper/2205.13600/) (2022)
- [DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems](https://mlsanity.com/paper/2206.00484/) (2022)
- [Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions](https://mlsanity.com/paper/2410.12773/) (2024)
- [Latent Exploration for Reinforcement Learning](https://mlsanity.com/paper/2305.20065/) (2023)
- [SAR: Generalization of Physiological Agility and Dexterity via Synergistic Action Representation](https://mlsanity.com/paper/2307.03716/) (2023)
- [Self Model for Embodied Intelligence: Modeling Full-Body Human Musculoskeletal System and Locomotion Control with Hierarchical Low-Dimensional Representation](https://mlsanity.com/paper/2312.05473/) (2023)
- [MuscleVAE: Model-Based Controllers of Muscle-Actuated Characters](https://mlsanity.com/paper/2312.07340/) (2023)
- [DynSyn: Dynamical Synergistic Representation for Efficient Learning and Control in Overactuated Embodied Systems](https://mlsanity.com/paper/2407.11472/) (2024)
- [MyoDex: A Generalizable Prior for Dexterous Manipulation](https://mlsanity.com/paper/2309.03130/) (2023)
- [Policy Adaptation from Foundation Model Feedback](https://mlsanity.com/paper/2212.07398/) (2022)
- [Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning](https://mlsanity.com/paper/2412.05515/) (2024)
- [Quantifying Performance of Bipedal Standing with Multi-channel EMG](https://mlsanity.com/paper/1711.07894/) (2017)
- [Motion Control of High-Dimensional Musculoskeletal Systems with Hierarchical Model-Based Planning](https://mlsanity.com/paper/2505.08238/) (2025)

## Abstract (arXiv)

Discovering effective reward functions remains a fundamental challenge in motor control of high-dimensional musculoskeletal systems. While humans can describe movement goals explicitly such as "walking forward with an upright posture," the underlying control strategies that realize these goals are largely implicit, making it difficult to directly design rewards from high-level goals and natural language descriptions. We introduce Motion from Vision-Language Representation (MoVLR), a framework that leverages vision-language models (VLMs) to bridge the gap between goal specification and movement control. Rather than relying on handcrafted rewards, MoVLR iteratively explores the reward space through iterative interaction between control optimization and VLM feedback, aligning control policies with physically coordinated behaviors. Our approach transforms language and vision-based assessments into structured guidance for embodied learning, enabling the discovery and refinement of reward functions for high-dimensional musculoskeletal locomotion and manipulation. These results suggest that VLMs can effectively ground abstract motion descriptions in the implicit principles governing physiological motor control.