# K-nearest Multi-agent Deep Reinforcement Learning for Collaborative Tasks with a Variable Number of Agents

arXiv: https://arxiv.org/abs/2201.07092 · HTML: https://mlsanity.com/paper/2201.07092/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 18 Jan 2022.

## Builds on (most cited first, 9 of 9)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Challenges of Real-World Reinforcement Learning](https://mlsanity.com/paper/1904.12901/) (2019)
- [An empirical investigation of the challenges of real-world reinforcement learning](https://mlsanity.com/paper/2003.11881/) (2020)
- [Dynamic Dispatching for Large-Scale Heterogeneous Fleet via Multi-agent Deep Reinforcement Learning](https://mlsanity.com/paper/2008.10713/) (2020)
- [Challenges of Applying Deep Reinforcement Learning in Dynamic Dispatching](https://mlsanity.com/paper/2011.05570/) (2020)

## Built on by (most cited first, 2 of 2)

- [Multicopy Reinforcement Learning Agents](https://mlsanity.com/paper/2309.10908/) (2023)
- [Onboard Mission Replanning for Adaptive Cooperative Multi-Robot Systems](https://mlsanity.com/paper/2506.06094/) (2025)

## Abstract (arXiv)

Traditionally, the performance of multi-agent deep reinforcement learning algorithms are demonstrated and validated in gaming environments where we often have a fixed number of agents. In many industrial applications, the number of available agents can change at any given day and even when the number of agents is known ahead of time, it is common for an agent to break during the operation and become unavailable for a period of time. In this paper, we propose a new deep reinforcement learning algorithm for multi-agent collaborative tasks with a variable number of agents. We demonstrate the application of our algorithm using a fleet management simulator developed by Hitachi to generate realistic scenarios in a production site.