# Sensor to Pixels: Decentralized Swarm Gathering via Image-Based Reinforcement Learning

arXiv: https://arxiv.org/abs/2601.03413 · HTML: https://mlsanity.com/paper/2601.03413/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 6 Jan 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 10 of 10)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [PettingZoo: Gym for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2009.14471/) (2020)
- [A Survey and Critique of Multiagent Deep Reinforcement Learning](https://mlsanity.com/paper/1810.05587/) (2018)
- [Deep Reinforcement Learning for Swarm Systems](https://mlsanity.com/paper/1807.06613/) (2018)
- [COME TOGETHER: Multi-Agent Geometric Consensus (Gathering, Rendezvous, Clustering, Aggregation)](https://mlsanity.com/paper/1902.01455/) (2019)
- [Continuous Time Gathering of Agents with Limited Visibility and Bearing-Only Sensing](https://mlsanity.com/paper/1510.09115/) (2015)
- [Local Interactions for Cohesive Flexible Swarms](https://mlsanity.com/paper/1903.09259/) (2019)
- [Cooperative Bearing-Only Target Pursuit via Multiagent Reinforcement Learning: Design and Experiment](https://mlsanity.com/paper/2503.08740/) (2025)

## Abstract (arXiv)

This study highlights the potential of image-based reinforcement learning methods for addressing swarm-related tasks. In multi-agent reinforcement learning, effective policy learning depends on how agents sense, interpret, and process inputs. Traditional approaches often rely on handcrafted feature extraction or raw vector-based representations, which limit the scalability and efficiency of learned policies concerning input order and size. In this work we propose an image-based reinforcement learning method for decentralized control of a multi-agent system, where observations are encoded as structured visual inputs that can be processed by Neural Networks, extracting its spatial features and producing novel decentralized motion control rules. We evaluate our approach on a multi-agent convergence task of agents with limited-range and bearing-only sensing that aim to keep the swarm cohesive during the aggregation. The algorithm's performance is evaluated against two benchmarks: an analytical solution proposed by Bellaiche and Bruckstein, which ensures convergence but progresses slowly, and VariAntNet, a neural network-based framework that converges much faster but shows medium success rates in hard constellations. Our method achieves high convergence, with a pace nearly matching that of VariAntNet. In some scenarios, it serves as the only practical alternative.