AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning

Arnu Pretorius, Scott Cameron, Elan van Biljon, Thomas Makkink, Shahil Mawjee, Jeremy du Plessis, Jonathan Shock, Alexandre Laterre, Karim Beguir

NeurIPS 2020 · Multi-agent systems and games › Games and equilibria · approach: Learning in Markov games · 5 citations (OpenAlex)

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
Use differentiable communication protocols instead of non-communicative information sharingNetworked MARL for water management · Water management system, α = 0.1equilibrium system payoffImproved
Use DIAL or CommNet instead of NeurCommNetworked MARL for water management · Water management system, α = 0.1equilibrium efficiencyHurt
Use NeurComm rather than the other tested algorithmsNetworked MARL for water management · Water management system, α = 0.1stable efficient equilibriumImproved
Use differentiable communication protocols rather than non-communicative approachesNetworked MARL for water management · Low resource regeneration ratesrestraintMixed
Set α = 0 rather than α = 0.1 (ablation)Networked MARL for water management · Water management system, low regeneration ratesrestraintHurt
Set α = 1 rather than α = 0.1 (ablation)Networked MARL for water management · Water management system, low regeneration ratesrestraintImproved
Set α = 1 rather than α = 0.1 (ablation)Non-communicative MARL algorithms · Water management system, α = 1system payoff at highest-payoff configurationHurt
Set α = 1 rather than α = 0.1 (ablation)ConseNet, DIAL, CommNet, and NeurComm · Water management system, α = 1system payoff at highest-payoff configurationImproved
Use NeurComm instead of other algorithmsNetworked MARL for water management · Water management system, α = 0.1dominant strategy cooperationImproved
Use ConseNet instead of non-communicative algorithmsNetworked MARL for water management · Water management systemequilibrium profileImproved
Operate IA2C, NA2C, or FPrint with α = 0 (ablation)Non-communicative MARL algorithms · Water management system, α = 0availability of full-cooperation configurationHurt
Use the low regeneration rate c = 0.03 rather than c = 0.042IA2C, NA2C, and FPrint · Water management system, α = 0.1restraint: 0.042 to 0.03Hurt

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