Research map / Multi-agent systems and games / Games and equilibria
A multi-agent reinforcement learning model of common-pool resource appropriation
Julien Pérolat, Joel Z. Leibo, Vinicius Zambaldi, Charles Beattie, Karl Tuyls, Thore Graepel
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| learn an appropriation policy through independent trial-and-error reinforcement learning | single-agent commons game · small map | sustainability | Improved |
| learn through independent reinforcement learning | multi-agent commons game · open map | efficiency | Mixed |
| enable the time-out beam tagging action (ablation) | multi-agent commons game · open map | sustainability | Improved |
| allow one agent, but not the other agents, to tag (ablation) | multi-agent commons game · open map | return | Improved |
| allow one agent, but not the other agents, to tag and establish a territory (ablation) | multi-agent commons game · open map | sustainability | Improved |
| make territorial exclusion easier with natural boundaries (ablation) | multi-agent commons game · maps with natural regions | equality | Hurt |
| remove walls, making territorial exclusion more difficult (ablation) | multi-agent commons game · region map with no walls | equality | Improved |
| add multiple entrances to regions, making territorial exclusion more difficult (ablation) | multi-agent commons game · multi-entrance region map | equality | Improved |
| make one region more productive than the others (ablation) | multi-agent commons game · unequal single-entrance region map | equality | Hurt |
Closest papers by meaning
- Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents (NeurIPS 2024 · similarity 0.85)
- LOPT: Learning Optimal Pigovian Tax in Sequential Social Dilemmas (NeurIPS 2025 · similarity 0.85)
- Tapes Together Strong: The Co-evolution of Computation and Cooperation (NeurIPS 2026 · similarity 0.85)
- Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games (NeurIPS 2024 · similarity 0.84)
- Aligning Individual and Collective Objectives in Multi-Agent Cooperation (NeurIPS 2024 · similarity 0.84)
- Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
