mlsanityData to 14 Oct 2026

Evolutionary Stability Does Not Guarantee Learning Accessibility: A Multi-Agent Reinforcement Learning Perspective on Cooperation Emergence

arXiv 2609.27664 ↗First posted 23 Sep 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Cooperation emergence is a central problem in multi-agent systems because decentralized agents must coordinate while adapting to the changing behavior of others. Evolutionary game theory identifies strategically stable outcomes, but stability under a population adjustment dynamic need not imply that finite-sample learning agents can reach the same outcome through local reward feedback. We study this distinction in a transparent three-agent governance-motivated game involving a government, a platform firm, and users. We derive replicator dynamics for the fixed stage-game incentives, evaluate the cooperative evolutionary basin on a symmetric initial-condition grid, and compare it with learning-basin estimates for three decentralized value-based learners. The learning analysis uses independent Q-learning with varepsilon-greedy action selection, scaled Boltzmann exploration, and SA--EA BQL under the same payoff environment and outcome criterion. The evolutionary basin has volume VE=1.00 on the sampled grid. The empirical learning basin is 0.88 for varepsilon-IQL and 0.00 for both scaled Boltzmann and SA--EA BQL. Diagnostic traces show that broader action diversity and nonzero value separation can coexist with failure to sustain the cooperative joint action in this fixed configuration. These results indicate that evolutionary stability and learning accessibility are distinct properties of a coupled game--learning system. The shared-bike setting is a motivating application; the broader contribution is a framework for comparing population-level stability with the finite-sample accessibility of cooperation under specified multi-agent learning dynamics.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 35 references that are in the map. First posted on arXiv 23 Sep 2026.

Builds on

11 of 35 references.

References · 11

  1. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  2. 2017Counterfactual Multi-Agent Policy Gradientscited by 751
  3. 2019The StarCraft Multi-Agent Challengecited by 597
  4. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 575
  5. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
  6. 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 379
  7. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 209
  8. 2018A Survey and Critique of Multiagent Deep Reinforcement Learningcited by 177
  9. 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 175
  10. 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 137
  11. 2021Cooperative Exploration for Multi-Agent Deep Reinforcement Learningcited by 57

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Multi-agent cooperation through learning-aware policy gradients
  2. 2024Mutation-Bias Learning in Games
  3. 2025Emergent Coordination and Phase Structure in Independent Multi-Agent Reinforcement Learning
  4. 2024Learning Fair Cooperation in Mixed-Motive Games with Indirect Reciprocity
  5. 2024Game Theory and Multi-Agent Reinforcement Learning : From Nash Equilibria to Evolutionary Dynamics
  6. 2026An Evolutionary Computation Framework for Multi-Agent Q-Learning with Mean-Field Environmental Feedback
  7. 2024Evolution of Societies via Reinforcement Learning
  8. 2024Emergent Cooperation under Uncertain Incentive Alignment