mlsanityData to 7 Oct 2026

The Importance of Credo in Multiagent Learning

arXiv 2204.07471 ↗First posted 15 Apr 2022cs.AIcited by 7

Not on the map. Why?

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.

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

Builds on

20 of 66 references.

References · 20

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  3. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 308
  4. 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 260
  5. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 206
  6. 2020Open Problems in Cooperative AIcited by 167
  7. 2018Inequity aversion improves cooperation in intertemporal social dilemmascited by 106
  8. 2020Learning to Incentivize Other Learning Agentscited by 55
  9. 2020Social diversity and social preferences in mixed-motive reinforcement learningcited by 49
  10. 2017Prosocial learning agents solve generalized Stag Hunts better than selfish onescited by 47
  11. 2019Multi-Agent Actor-Critic with Hierarchical Graph Attention Networkcited by 33
  12. 2018Evolving intrinsic motivations for altruistic behaviorcited by 30
8 more
  1. 2020Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferencescited by 21
  2. 2019Partner Selection for the Emergence of Cooperation in Multi-Agent Systems Using Reinforcement Learningcited by 20
  3. 2021An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learningcited by 20
  4. 2021Expected Value of Communication for Planning in Ad Hoc Teamworkcited by 19
  5. 2020D3C: Reducing the Price of Anarchy in Multi-Agent Learningcited by 16
  6. 2021Cooperation and Reputation Dynamics with Reinforcement Learningcited by 12
  7. 2021Cooperative and Competitive Biases for Multi-Agent Reinforcement Learningcited by 5
  8. 2020MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agentscited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 3.

7 papers.

  1. 2024Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmascited by 12
  2. 2022Exploring the Benefits of Teams in Multiagent Learningcited by 5
  3. 2024Emergent Cooperation under Uncertain Incentive Alignmentcited by 3
  4. 2023Presenting Multiagent Challenges in Team Sports Analyticscited by 2
  5. 2023Towards a Better Understanding of Learning with Multiagent Teamscited by 2
  6. 2023Learning to Learn Group Alignment: A Self-Tuning Credo Framework with Multiagent Teamscited by 1
  7. 2024Preference-based opponent shaping in differentiable gamescited by 0