# A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks

arXiv: https://arxiv.org/abs/2007.04979 · HTML: https://mlsanity.com/paper/2007.04979/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2020.

## Built on by (most cited first, 30 of 52)

- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Building Cooperative Embodied Agents Modularly with Large Language Models](https://mlsanity.com/paper/2307.02485/) (2023)
- [Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots](https://mlsanity.com/paper/2310.13724/) (2023)
- [Affordances from Human Videos as a Versatile Representation for Robotics](https://mlsanity.com/paper/2304.08488/) (2023)
- [Visual Room Rearrangement](https://mlsanity.com/paper/2103.16544/) (2021)
- [MindAgent: Emergent Gaming Interaction](https://mlsanity.com/paper/2309.09971/) (2023)
- [ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes](https://mlsanity.com/paper/2304.04321/) (2023)
- [LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models](https://mlsanity.com/paper/2310.03903/) (2023)
- [Cooperative Exploration for Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/2107.11444/) (2021)
- [COMBO: Compositional World Models for Embodied Multi-Agent Cooperation](https://mlsanity.com/paper/2404.10775/) (2024)
- [Retrospectives on the Embodied AI Workshop](https://mlsanity.com/paper/2210.06849/) (2022)
- [Multi-agent Embodied AI: Advances and Future Directions](https://mlsanity.com/paper/2505.05108/) (2025)
- [LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments](https://mlsanity.com/paper/2407.10031/) (2024)
- [Pretrained Language Models as Visual Planners for Human Assistance](https://mlsanity.com/paper/2304.09179/) (2023)
- [The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation](https://mlsanity.com/paper/2108.11550/) (2021)
- [Last-Mile Embodied Visual Navigation](https://mlsanity.com/paper/2211.11746/) (2022)
- [IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction](https://mlsanity.com/paper/2408.10455/) (2024)
- [GridToPix: Training Embodied Agents with Minimal Supervision](https://mlsanity.com/paper/2105.00931/) (2021)
- [Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents](https://mlsanity.com/paper/2110.05769/) (2021)
- [Collaborative Visual Navigation](https://mlsanity.com/paper/2107.01151/) (2021)
- [Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2108.03319/) (2021)
- [VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning](https://mlsanity.com/paper/2506.09049/) (2025)
- [Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration](https://mlsanity.com/paper/2108.06038/) (2021)
- [Shaping embodied agent behavior with activity-context priors from egocentric video](https://mlsanity.com/paper/2110.07692/) (2021)
- [Adaptive Coordination in Social Embodied Rearrangement](https://mlsanity.com/paper/2306.00087/) (2023)
- [Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge](https://mlsanity.com/paper/2411.01796/) (2024)
- [Virtual Community: An Open World for Humans, Robots, and Society](https://mlsanity.com/paper/2508.14893/) (2025)
- [ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward](https://mlsanity.com/paper/2210.04365/) (2022)
- [Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge](https://mlsanity.com/paper/2109.09531/) (2021)

## Abstract (arXiv)

Autonomous agents must learn to collaborate. It is not scalable to develop a new centralized agent every time a task's difficulty outpaces a single agent's abilities. While multi-agent collaboration research has flourished in gridworld-like environments, relatively little work has considered visually rich domains. Addressing this, we introduce the novel task FurnMove in which agents work together to move a piece of furniture through a living room to a goal. Unlike existing tasks, FurnMove requires agents to coordinate at every timestep. We identify two challenges when training agents to complete FurnMove: existing decentralized action sampling procedures do not permit expressive joint action policies and, in tasks requiring close coordination, the number of failed actions dominates successful actions. To confront these challenges we introduce SYNC-policies (synchronize your actions coherently) and CORDIAL (coordination loss). Using SYNC-policies and CORDIAL, our agents achieve a 58% completion rate on FurnMove, an impressive absolute gain of 25 percentage points over competitive decentralized baselines. Our dataset, code, and pretrained models are available at https://unnat.github.io/cordial-sync .