AI Paper Atlas

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

NeurIPS 2017 · Multi-agent systems and games › Games and equilibria · approach: Cooperation and social dilemmas

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 changedWhereMeasuredEffect
learn an appropriation policy through independent trial-and-error reinforcement learningsingle-agent commons game · small mapsustainabilityImproved
learn through independent reinforcement learningmulti-agent commons game · open mapefficiencyMixed
enable the time-out beam tagging action (ablation)multi-agent commons game · open mapsustainabilityImproved
allow one agent, but not the other agents, to tag (ablation)multi-agent commons game · open mapreturnImproved
allow one agent, but not the other agents, to tag and establish a territory (ablation)multi-agent commons game · open mapsustainabilityImproved
make territorial exclusion easier with natural boundaries (ablation)multi-agent commons game · maps with natural regionsequalityHurt
remove walls, making territorial exclusion more difficult (ablation)multi-agent commons game · region map with no wallsequalityImproved
add multiple entrances to regions, making territorial exclusion more difficult (ablation)multi-agent commons game · multi-entrance region mapequalityImproved
make one region more productive than the others (ablation)multi-agent commons game · unequal single-entrance region mapequalityHurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy