# Celebrating Diversity in Shared Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2106.02195 · HTML: https://mlsanity.com/paper/2106.02195/

## Key facts

- Cited by 98 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 50 references that are in the map.
- First posted on arXiv 4 Jun 2021.

## Builds on (most cited first, 30 of 35)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (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)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1905.05408/) (2019)
- [Dynamics-Aware Unsupervised Discovery of Skills](https://mlsanity.com/paper/1907.01657/) (2019)
- [Agent57: Outperforming the Atari Human Benchmark](https://mlsanity.com/paper/2003.13350/) (2020)
- [QPLEX: Duplex Dueling Multi-Agent Q-Learning](https://mlsanity.com/paper/2008.01062/) (2020)
- [Google Research Football: A Novel Reinforcement Learning Environment](https://mlsanity.com/paper/1907.11180/) (2019)
- [Never Give Up: Learning Directed Exploration Strategies](https://mlsanity.com/paper/2002.06038/) (2020)
- [Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2006.10800/) (2020)
- [MAVEN: Multi-Agent Variational Exploration](https://mlsanity.com/paper/1910.07483/) (2019)
- [ROMA: Multi-Agent Reinforcement Learning with Emergent Roles](https://mlsanity.com/paper/2003.08039/) (2020)
- [RODE: Learning Roles to Decompose Multi-Agent Tasks](https://mlsanity.com/paper/2010.01523/) (2020)
- [Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills](https://mlsanity.com/paper/2002.03647/) (2020)
- [Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks](https://mlsanity.com/paper/1812.09755/) (2018)
- [Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2006.07169/) (2020)
- [Deep Coordination Graphs](https://mlsanity.com/paper/1910.00091/) (2019)
- [Off-Policy Multi-Agent Decomposed Policy Gradients](https://mlsanity.com/paper/2007.12322/) (2020)
- [Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing](https://mlsanity.com/paper/2102.07475/) (2021)
- [Learning Nearly Decomposable Value Functions Via Communication Minimization](https://mlsanity.com/paper/1910.05366/) (2019)
- [Influence-Based Multi-Agent Exploration](https://mlsanity.com/paper/1910.05512/) (2019)
- [Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1901.09207/) (2019)
- [Guided Deep Reinforcement Learning for Swarm Systems](https://mlsanity.com/paper/1709.06011/) (2017)
- [Emergent Social Learning via Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2010.00581/) (2020)
- [Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2006.04222/) (2020)

## Built on by (most cited first, 30 of 98)

- [Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2106.03400/) (2021)
- [Towards a Standardised Performance Evaluation Protocol for Cooperative MARL](https://mlsanity.com/paper/2209.10485/) (2022)
- [Heterogeneous Multi-Robot Reinforcement Learning](https://mlsanity.com/paper/2301.07137/) (2023)
- [PolyNet: Learning Diverse Solution Strategies for Neural Combinatorial Optimization](https://mlsanity.com/paper/2402.14048/) (2024)
- [Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2206.07505/) (2022)
- [PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination](https://mlsanity.com/paper/2301.06387/) (2023)
- [Order Matters: Agent-by-agent Policy Optimization](https://mlsanity.com/paper/2302.06205/) (2023)
- [TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play](https://mlsanity.com/paper/2302.07515/) (2023)
- [Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition](https://mlsanity.com/paper/2211.12712/) (2022)
- [TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations](https://mlsanity.com/paper/2110.04507/) (2021)
- [Pretraining in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2211.03959/) (2022)
- [Generating Teammates for Training Robust Ad Hoc Teamwork Agents via Best-Response Diversity](https://mlsanity.com/paper/2207.14138/) (2022)
- [LDSA: Learning Dynamic Subtask Assignment in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2205.02561/) (2022)
- [ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency](https://mlsanity.com/paper/2211.16068/) (2022)
- [System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning](https://mlsanity.com/paper/2305.02128/) (2023)
- [Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2405.15054/) (2024)
- [HyperMARL: Adaptive Hypernetworks for Multi-Agent RL](https://mlsanity.com/paper/2412.04233/) (2024)
- [Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2210.03022/) (2022)
- [Non-Linear Coordination Graphs](https://mlsanity.com/paper/2211.08404/) (2022)
- [Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations](https://mlsanity.com/paper/2305.13030/) (2023)
- [FoX: Formation-aware exploration in multi-agent reinforcement learning](https://mlsanity.com/paper/2308.11272/) (2023)
- [Multi-Sender Persuasion: A Computational Perspective](https://mlsanity.com/paper/2402.04971/) (2024)
- [Interaction Pattern Disentangling for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2207.03902/) (2022)
- [Semantically Aligned Task Decomposition in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2305.10865/) (2023)
- [Breaking the Curse of Dimensionality in Multiagent State Space: A Unified Agent Permutation Framework](https://mlsanity.com/paper/2203.05285/) (2022)
- [Learning Diverse Risk Preferences in Population-based Self-play](https://mlsanity.com/paper/2305.11476/) (2023)
- [Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing](https://mlsanity.com/paper/2402.02097/) (2024)
- [Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration](https://mlsanity.com/paper/2404.03869/) (2024)
- [Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2410.08540/) (2024)
- [Towards Global Optimality in Cooperative MARL with the Transformation And Distillation Framework](https://mlsanity.com/paper/2207.11143/) (2022)

## Abstract (arXiv)

Recently, deep multi-agent reinforcement learning (MARL) has shown the promise to solve complex cooperative tasks. Its success is partly because of parameter sharing among agents. However, such sharing may lead agents to behave similarly and limit their coordination capacity. In this paper, we aim to introduce diversity in both optimization and representation of shared multi-agent reinforcement learning. Specifically, we propose an information-theoretical regularization to maximize the mutual information between agents' identities and their trajectories, encouraging extensive exploration and diverse individualized behaviors. In representation, we incorporate agent-specific modules in the shared neural network architecture, which are regularized by L1-norm to promote learning sharing among agents while keeping necessary diversity. Empirical results show that our method achieves state-of-the-art performance on Google Research Football and super hard StarCraft II micromanagement tasks.