# Coach-assisted Multi-Agent Reinforcement Learning Framework for Unexpected Crashed Agents

arXiv: https://arxiv.org/abs/2203.08454 · HTML: https://mlsanity.com/paper/2203.08454/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 16 Mar 2022.

## Builds on (most cited first, 21 of 21)

- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [Value-Decomposition Networks For Cooperative Multi-Agent Learning](https://mlsanity.com/paper/1706.05296/) (2017)
- [Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey](https://mlsanity.com/paper/2009.13303/) (2020)
- [QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1905.05408/) (2019)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [QPLEX: Duplex Dueling Multi-Agent Q-Learning](https://mlsanity.com/paper/2008.01062/) (2020)
- [DARLA: Improving Zero-Shot Transfer in Reinforcement Learning](https://mlsanity.com/paper/1707.08475/) (2017)
- [Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability](https://mlsanity.com/paper/1703.06182/) (2017)
- [Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1702.08887/) (2017)
- [Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games](https://mlsanity.com/paper/1703.10069/) (2017)
- [Learning to Schedule Communication in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1902.01554/) (2019)
- [Qatten: A General Framework for Cooperative Multiagent Reinforcement Learning](https://mlsanity.com/paper/2002.03939/) (2020)
- [Meta Reinforcement Learning for Sim-to-real Domain Adaptation](https://mlsanity.com/paper/1909.12906/) (2019)
- [Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer](https://mlsanity.com/paper/1906.04452/) (2019)
- [Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances](https://mlsanity.com/paper/1912.03821/) (2019)

## Built on by (most cited first, 3 of 3)

- [LDSA: Learning Dynamic Subtask Assignment in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2205.02561/) (2022)
- [MA2CL:Masked Attentive Contrastive Learning for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2306.02006/) (2023)
- [ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools](https://mlsanity.com/paper/2510.00023/) (2025)

## Abstract (arXiv)

Multi-agent reinforcement learning is difficult to be applied in practice, which is partially due to the gap between the simulated and real-world scenarios. One reason for the gap is that the simulated systems always assume that the agents can work normally all the time, while in practice, one or more agents may unexpectedly "crash" during the coordination process due to inevitable hardware or software failures. Such crashes will destroy the cooperation among agents, leading to performance degradation. In this work, we present a formal formulation of a cooperative multi-agent reinforcement learning system with unexpected crashes. To enhance the robustness of the system to crashes, we propose a coach-assisted multi-agent reinforcement learning framework, which introduces a virtual coach agent to adjust the crash rate during training. We design three coaching strategies and the re-sampling strategy for our coach agent. To the best of our knowledge, this work is the first to study the unexpected crashes in the multi-agent system. Extensive experiments on grid-world and StarCraft II micromanagement tasks demonstrate the efficacy of adaptive strategy compared with the fixed crash rate strategy and curriculum learning strategy. The ablation study further illustrates the effectiveness of our re-sampling strategy.