# Robust Event-Driven Interactions in Cooperative Multi-Agent Learning

arXiv: https://arxiv.org/abs/2204.03361 · HTML: https://mlsanity.com/paper/2204.03361/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 38 references that are in the map.
- First posted on arXiv 7 Apr 2022.

## Builds on (most cited first, 13 of 13)

- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Learning to Schedule Communication in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1902.01554/) (2019)
- [On the Robustness of Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.03722/) (2020)
- [Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning](https://mlsanity.com/paper/2108.03803/) (2021)
- [A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning](https://mlsanity.com/paper/1907.03053/) (2019)
- [Communication-Efficient Policy Gradient Methods for Distributed Reinforcement Learning](https://mlsanity.com/paper/1812.03239/) (2018)
- [Event-triggered Learning](https://mlsanity.com/paper/1904.03042/) (2019)
- [A Theory of the Risk for Optimization with Relaxation and its Application to Support Vector Machines](https://mlsanity.com/paper/2004.05839/) (2020)
- [Planning Not to Talk: Multiagent Systems that are Robust to Communication Loss](https://mlsanity.com/paper/2201.06619/) (2022)

## Abstract (arXiv)

We present an approach to reduce the communication required between agents in a Multi-Agent learning system by exploiting the inherent robustness of the underlying Markov Decision Process. We compute so-called robustness surrogate functions (off-line), that give agents a conservative indication of how far their state measurements can deviate before they need to update other agents in the system. This results in fully distributed decision functions, enabling agents to decide when it is necessary to update others. We derive bounds on the optimality of the resulting systems in terms of the discounted sum of rewards obtained, and show these bounds are a function of the design parameters. Additionally, we extend the results for the case where the robustness surrogate functions are learned from data, and present experimental results demonstrating a significant reduction in communication events between agents.