# The Importance of Credo in Multiagent Learning

arXiv: https://arxiv.org/abs/2204.07471 · HTML: https://mlsanity.com/paper/2204.07471/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 66 references that are in the map.
- First posted on arXiv 15 Apr 2022.

## Builds on (most cited first, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Emergent Tool Use From Multi-Agent Autocurricula](https://mlsanity.com/paper/1909.07528/) (2019)
- [Human-level performance in first-person multiplayer games with population-based deep reinforcement learning](https://mlsanity.com/paper/1807.01281/) (2018)
- [Multi-agent Reinforcement Learning in Sequential Social Dilemmas](https://mlsanity.com/paper/1702.03037/) (2017)
- [Open Problems in Cooperative AI](https://mlsanity.com/paper/2012.08630/) (2020)
- [Inequity aversion improves cooperation in intertemporal social dilemmas](https://mlsanity.com/paper/1803.08884/) (2018)
- [Learning to Incentivize Other Learning Agents](https://mlsanity.com/paper/2006.06051/) (2020)
- [Social diversity and social preferences in mixed-motive reinforcement learning](https://mlsanity.com/paper/2002.02325/) (2020)
- [Prosocial learning agents solve generalized Stag Hunts better than selfish ones](https://mlsanity.com/paper/1709.02865/) (2017)
- [Multi-Agent Actor-Critic with Hierarchical Graph Attention Network](https://mlsanity.com/paper/1909.12557/) (2019)
- [Evolving intrinsic motivations for altruistic behavior](https://mlsanity.com/paper/1811.05931/) (2018)
- [Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences](https://mlsanity.com/paper/2011.05373/) (2020)
- [Partner Selection for the Emergence of Cooperation in Multi-Agent Systems Using Reinforcement Learning](https://mlsanity.com/paper/1902.03185/) (2019)
- [An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning](https://mlsanity.com/paper/2103.06224/) (2021)
- [Expected Value of Communication for Planning in Ad Hoc Teamwork](https://mlsanity.com/paper/2103.01171/) (2021)
- [D3C: Reducing the Price of Anarchy in Multi-Agent Learning](https://mlsanity.com/paper/2010.00575/) (2020)
- [Cooperation and Reputation Dynamics with Reinforcement Learning](https://mlsanity.com/paper/2102.07523/) (2021)
- [Cooperative and Competitive Biases for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2101.06890/) (2021)
- [MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents](https://mlsanity.com/paper/2010.07893/) (2020)

## Built on by (most cited first, 7 of 7)

- [Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmas](https://mlsanity.com/paper/2402.17270/) (2024)
- [Exploring the Benefits of Teams in Multiagent Learning](https://mlsanity.com/paper/2205.02328/) (2022)
- [Emergent Cooperation under Uncertain Incentive Alignment](https://mlsanity.com/paper/2401.12646/) (2024)
- [Presenting Multiagent Challenges in Team Sports Analytics](https://mlsanity.com/paper/2303.13660/) (2023)
- [Towards a Better Understanding of Learning with Multiagent Teams](https://mlsanity.com/paper/2306.16205/) (2023)
- [Learning to Learn Group Alignment: A Self-Tuning Credo Framework with Multiagent Teams](https://mlsanity.com/paper/2304.07337/) (2023)
- [Preference-based opponent shaping in differentiable games](https://mlsanity.com/paper/2412.03072/) (2024)

## Abstract (arXiv)

We propose a model for multi-objective optimization, a credo, for agents in a system that are configured into multiple groups (i.e., teams). Our model of credo regulates how agents optimize their behavior for the groups they belong to. We evaluate credo in the context of challenging social dilemmas with reinforcement learning agents. Our results indicate that the interests of teammates, or the entire system, are not required to be fully aligned for achieving globally beneficial outcomes. We identify two scenarios without full common interest that achieve high equality and significantly higher mean population rewards compared to when the interests of all agents are aligned.