mlsanityData to 14 Oct 2026

The Role of Network Topology and Opponent Information in Shaping Cooperation in Multi-Agent Reinforcement Learning Systems

arXiv 2608.28977 ↗First posted 29 Aug 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Several works have investigated the influence of graph topology on cooperation among artificial agents, while the majority of the literature has focused on modelling agents' adaptation through strategy imitation, which relies solely on the cumulative payoffs of others. This paper investigates scenarios in which each agent learns to play the two-player Iterated Prisoner's Dilemma (IPD) using deep reinforcement learning. Each agent is represented as a node in a graph, where its neighbours constitute the pool of opponents with whom it can interact. During each IPD episode, agents are provided with different types of information about their opponent, consisting of action history and opponent identity. Experimental results across different graph topologies show that the number of neighbours per node and the average path length are the main factors affecting the emergence of cooperation. We also show that, while partner selection fosters mutual cooperation by limiting the diversity of the opponent pool, providing agents with the identity of their opponent hinders the proliferation of cooperative strategies.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 45 references that are in the map. First posted on arXiv 29 Aug 2026.

Builds on

11 of 45 references.

References · 11

  1. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  2. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  3. 2017Learning with Opponent-Learning Awarenesscited by 222
  4. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 209
  5. 2018Inequity aversion improves cooperation in intertemporal social dilemmascited by 106
  6. 2021Deep Multiagent Reinforcement Learning: Challenges and Directionscited by 42
  7. 2019Partner Selection for the Emergence of Cooperation in Multi-Agent Systems Using Reinforcement Learningcited by 20
  8. 2021Cooperation and Reputation Dynamics with Reinforcement Learningcited by 13
  9. 2023Investigating the Impact of Direct Punishment on the Emergence of Cooperation in Multi-Agent Reinforcement Learning Systemscited by 5
  10. 2014Learning dynamics explains human behavior in Prisoner's Dilemma on networkscited by 2
  11. 2022Enabling Imitation-Based Cooperation in Dynamic Social Networkscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Enhancing Cooperation through Selective Interaction and Long-term Experiences in Multi-Agent Reinforcement Learning
  2. 2026Exploring cooperation mechanisms via deep reinforcement learning in network common-pool resource games
  3. 2024Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies
  4. 2025Topology Enhanced MARL for Multi-Agent Cooperative Decision-Making of CAVs
  5. 2026Investigating the Impact of Subgraph Social Structure Preference on the Strategic Behavior of Networked Mixed-Motive Learning Agents ↗
  6. 2025Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks
  7. 2024Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning
  8. 2025Convergence and Connectivity: Dynamics of Multi-Agent Q-Learning in Random Networks