MA-VLCM: A Vision Language Critic Model for Value Estimation of Policies in Multi-Agent Team Settings
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915867253538816 |
|---|---|
| author | Shaik, Shahil Parameshwaran, Aditya Nayak, Anshul Smereka, Jonathon M. Wang, Yue |
| author_facet | Shaik, Shahil Parameshwaran, Aditya Nayak, Anshul Smereka, Jonathon M. Wang, Yue |
| contents | Multi-agent reinforcement learning (MARL) commonly relies on a centralized critic to estimate the value function. However, learning such a critic from scratch is highly sample-inefficient and often lacks generalization across environments. At the same time, large vision-language-action models (VLAs) trained on internet-scale data exhibit strong multimodal reasoning and zero-shot generalization capabilities, yet directly deploying them for robotic execution remains computationally prohibitive, particularly in heterogeneous multi-robot systems with diverse embodiments and resource constraints. To address these challenges, we propose Multi-Agent Vision-Language-Critic Models (MA-VLCM), a framework that replaces the learned centralized critic in MARL with a pretrained vision-language model fine-tuned to evaluate multi-agent behavior. MA-VLCM acts as a centralized critic conditioned on natural language task descriptions, visual trajectory observations, and structured multi-agent state information. By eliminating critic learning during policy optimization, our approach significantly improves sample efficiency while producing compact execution policies suitable for deployment on resource-constrained robots. Results show good zero-shot return estimation on models with differing VLM backbones on in-distribution and out-of-distribution scenarios in multi-agent team settings |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15418 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MA-VLCM: A Vision Language Critic Model for Value Estimation of Policies in Multi-Agent Team Settings Shaik, Shahil Parameshwaran, Aditya Nayak, Anshul Smereka, Jonathon M. Wang, Yue Robotics Artificial Intelligence Multi-agent reinforcement learning (MARL) commonly relies on a centralized critic to estimate the value function. However, learning such a critic from scratch is highly sample-inefficient and often lacks generalization across environments. At the same time, large vision-language-action models (VLAs) trained on internet-scale data exhibit strong multimodal reasoning and zero-shot generalization capabilities, yet directly deploying them for robotic execution remains computationally prohibitive, particularly in heterogeneous multi-robot systems with diverse embodiments and resource constraints. To address these challenges, we propose Multi-Agent Vision-Language-Critic Models (MA-VLCM), a framework that replaces the learned centralized critic in MARL with a pretrained vision-language model fine-tuned to evaluate multi-agent behavior. MA-VLCM acts as a centralized critic conditioned on natural language task descriptions, visual trajectory observations, and structured multi-agent state information. By eliminating critic learning during policy optimization, our approach significantly improves sample efficiency while producing compact execution policies suitable for deployment on resource-constrained robots. Results show good zero-shot return estimation on models with differing VLM backbones on in-distribution and out-of-distribution scenarios in multi-agent team settings |
| title | MA-VLCM: A Vision Language Critic Model for Value Estimation of Policies in Multi-Agent Team Settings |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2603.15418 |