# Decentralized Multi-Agents by Imitation of a Centralized Controller

arXiv: https://arxiv.org/abs/1902.02311 · HTML: https://mlsanity.com/paper/1902.02311/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 6 Feb 2019.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Built on by (most cited first, 5 of 5)

- [An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2409.03052/) (2024)
- [AgentMixer: Multi-Agent Correlated Policy Factorization](https://mlsanity.com/paper/2401.08728/) (2024)
- [The Multi-Agent Pickup and Delivery Problem: MAPF, MARL and Its Warehouse Applications](https://mlsanity.com/paper/2203.07092/) (2022)
- [Interactive Distillation for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2601.05407/) (2026)
- [Learning-Accelerated Optimization-based Trajectory Planning for Cooperative Aerial-Ground Handover Missions](https://mlsanity.com/paper/2605.19562/) (2026)

## Abstract (arXiv)

We consider a multi-agent reinforcement learning problem where each agent seeks to maximize a shared reward while interacting with other agents, and they may or may not be able to communicate. Typically the agents do not have access to other agent policies and thus each agent is situated in a non-stationary and partially-observable environment. In order to obtain multi-agents that act in a decentralized manner, we introduce a novel algorithm under the popular framework of centralized training, but decentralized execution. This training framework first obtains solutions to a multi-agent problem with a single centralized joint-space learner, which is then used to guide imitation learning for independent decentralized multi-agents. This framework has the flexibility to use any reinforcement learning algorithm to obtain the expert as well as any imitation learning algorithm to obtain the decentralized agents. This is in contrast to other multi-agent learning algorithms that, for example, can require more specific structures. We present some theoretical bounds for our method, and we show that one can obtain decentralized solutions to a multi-agent problem through imitation learning.