# Improving Sample Efficiency in Multi-Agent Reinforcement Learning for Simulated Football Games via Exploration

arXiv: https://arxiv.org/abs/2503.13077 · HTML: https://mlsanity.com/paper/2503.13077/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Google Research Football: A Novel Reinforcement Learning Environment](https://mlsanity.com/paper/1907.11180/) (2019)
- [From Motor Control to Team Play in Simulated Humanoid Football](https://mlsanity.com/paper/2105.12196/) (2021)
- [Real World Games Look Like Spinning Tops](https://mlsanity.com/paper/2004.09468/) (2020)
- [Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning](https://mlsanity.com/paper/2402.04080/) (2024)
- [Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers](https://mlsanity.com/paper/2212.11498/) (2022)
- [TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play](https://mlsanity.com/paper/2302.07515/) (2023)
- ["It's Unwieldy and It Takes a Lot of Time." Challenges and Opportunities for Creating Agents in Commercial Games](https://mlsanity.com/paper/2009.00541/) (2020)
- [Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment](https://mlsanity.com/paper/2406.01103/) (2024)
- [Training Interactive Agent in Large FPS Game Map with Rule-enhanced Reinforcement Learning](https://mlsanity.com/paper/2410.04936/) (2024)
- [AI-Olympics: Exploring the Generalization of Agents through Open Competitions](https://mlsanity.com/paper/2405.14358/) (2024)

## Built on by (most cited first, 1 of 1)

- [Generative World Models of Tasks: LLM-Driven Hierarchical Scaffolding for Embodied Agents](https://mlsanity.com/paper/2509.04731/) (2025)

## Abstract (arXiv)

Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often demand extensive training time, which inhibits their application for game-AI in standard game development. For instance, the state-of-the-art method TiZero takes 40 days to train high-quality policies for a football environment. In this paper, we hypothesize that better exploration mechanisms can improve the sample efficiency of multi-agent methods. Thereby, we propose utilizing a random network distillation bonus within the multi-agent TiZero framework, aiming to promote exploration. Additionally, we introduce architectural modifications to the original algorithm to enhance TiZero's computational efficiency. We evaluate the sample efficiency of our approach against original TiZero through extensive experiments. Our results show that random network distillation improves the sample efficiency per training phase by 13.3% compared with the original TiZero, enhancing generalization and adaptability to previously difficult scenarios. This highlights the better applicability of our variant in practical game development settings. Lastly, we qualitatively evaluate the gameplay of the produced models against a heuristic AI. We find that random network distillation leads to a higher accuracy in shooting, and it achieves higher behavioral stability as shown by the lower standard deviation achieved in gameplay metrics. The code is available at https://github.com/electronicarts/marling.