mlsanityData to 7 Oct 2026

Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity

arXiv 2110.04041 ↗First posted 8 Oct 2021cs.AIcited by 22

Not on the map. Why?

Abstract (arXiv)

Strategic diversity is often essential in games: in multi-player games, for example, evaluating a player against a diverse set of strategies will yield a more accurate estimate of its performance. Furthermore, in games with non-transitivities diversity allows a player to cover several winning strategies. However, despite the significance of strategic diversity, training agents that exhibit diverse behaviour remains a challenge. In this paper we study how to construct diverse populations of agents by carefully structuring how individuals within a population interact. Our approach is based on interaction graphs, which control the flow of information between agents during training and can encourage agents to specialise on different strategies, leading to improved overall performance. We provide evidence for the importance of diversity in multi-agent training and analyse the effect of applying different interaction graphs on the training trajectories, diversity and performance of populations in a range of games. This is an extended version of the long abstract published at AAMAS.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 15 of its 31 references that are in the map. First posted on arXiv 8 Oct 2021.

Builds on

15 of 31 references.

References · 15

  1. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  2. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 734
  3. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 268
  4. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
  5. 2016Variational Intrinsic Controlcited by 262
  6. 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 260
  7. 2017One-Shot Visual Imitation Learning via Meta-Learningcited by 225
  8. 2017Stochastic Neural Networks for Hierarchical Reinforcement Learningcited by 124
  9. 2018The Mechanics of n-Player Differentiable Gamescited by 118
  10. 2019Open-ended Learning in Symmetric Zero-sum Gamescited by 96
  11. 2017Meta Learning Shared Hierarchiescited by 93
  12. 2019Emergent Coordination Through Competitioncited by 57
3 more
  1. 2020Social diversity and social preferences in mixed-motive reinforcement learningcited by 49
  2. 2018Re-evaluating Evaluationcited by 47
  3. 2013Graphical Models for Game Theorycited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 6; 2023: 5; 2024: 5; 2025: 1; 2026: 3.

22 papers.

Sort:

By area:

  1. 2021Collaborating with Humans without Human Datacited by 139
  2. 2023Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biasedcited by 37
  3. 2022K-level Reasoning for Zero-Shot Coordination in Hanabicited by 30
  4. 2023MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learningcited by 30
  5. 2024A Survey on Self-play Methods in Reinforcement Learningcited by 26
  6. 2022NeuPL: Neural Population Learningcited by 14
  7. 2022Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENScited by 10
  8. 2021Lyapunov Exponents for Diversity in Differentiable Gamescited by 8
  9. 2022Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Gamescited by 8
  10. 2023Learning Diverse Risk Preferences in Population-based Self-playcited by 6
  11. 2024Neural Population Learning beyond Symmetric Zero-sum Gamescited by 4
  12. 2024Multi-Agent Diagnostics for Robustness via Illuminated Diversitycited by 4
10 more
  1. 2024Role Play: Learning Adaptive Role-Specific Strategies in Multi-Agent Interactionscited by 3
  2. 2022Watts: Infrastructure for Open-Ended Learningcited by 2
  3. 2023Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmascited by 2
  4. 2026GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learningcited by 2
  5. 2024Rethinking Teacher-Student Curriculum Learning through the Cooperative Mechanics of Experiencecited by 1
  6. 2025Robust Agents in Open-Ended Worldscited by 1
  7. 2022Principal Trade-off Analysiscited by 0
  8. 2023Centralized control for multi-agent RL in a complex Real-Time-Strategy gamecited by 0
  9. 2026Adaptive Human-AI Coordination via Hierarchical Action Disentanglementcited by 0
  10. 2026Partner-Aware Hierarchical Skill Discovery for Robust Human-AI Collaborationcited by 0