# Distributed Dexterous Manipulation with Spatially Conditioned Multi-Agent Transformers

arXiv: https://arxiv.org/abs/2609.06930 · HTML: https://mlsanity.com/paper/2609.06930/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 53 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1905.05408/) (2019)
- [Multi-Agent Reinforcement Learning is a Sequence Modeling Problem](https://mlsanity.com/paper/2205.14953/) (2022)
- [Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions](https://mlsanity.com/paper/2309.10150/) (2023)
- [PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav](https://mlsanity.com/paper/2301.07302/) (2023)
- [Data-efficient Deep Reinforcement Learning for Dexterous Manipulation](https://mlsanity.com/paper/1704.03073/) (2017)
- [Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient](https://mlsanity.com/paper/2406.00681/) (2024)
- [Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization](https://mlsanity.com/paper/2307.11620/) (2023)

## Abstract (arXiv)

Distributed Dexterous Manipulation (DDM) is a novel paradigm that presents significant control challenges due to high action-space redundancy, inter-robot cooperation, and dynamic object-robot interactions. This paper introduces a framework based on spatially conditioned Multi-Agent Transformers (MATs) to efficiently learn robust control policies for a DDM system grounded in an array of 64 soft delta robots arranged in an 8x8 grid. Our three core contributions are: (i) an MAT with adaptive layer norm for compute efficiency, (ii) spatial contrastive embeddings to ground transformer embeddings in the spatial configuration of the robots, and (iii) an MAT-based behavior cloning method fine-tuned using Soft Actor Critic. We also propose an action selection formulation to analyze the trade-off between task performance and the number of robots utilized. Our experiments show that MATs iteratively refine their actions through the stacked attention blocks. This further informs the benefit of spatial conditioning in transformers to learn DDM policies. We demonstrate long-horizon planar manipulation tasks with objects of various geometries in simulation and real-world. Finally, we show how action selection mitigates robot maintenance by reducing wear and tear due to inter-robot collisions while maintaining the ability to manipulate objects along various trajectories in the real-world, achieving an average error of ~1.5 cm, while using ~65% fewer robots.