AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

Multiagent Evaluation Mechanisms

Tal Alon, Magdalen Dobson, Ariel Procaccia, Inbal Talgam-Cohen, Jamie Tucker-Foltz

AAAI 2020 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping

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 a linear mechanism with beta=(1,1) instead of per-agent mechanismstwo-agent study-vs-cheat instance · Example 2.1, p=6all agents incentivized to study: marginal benefit 10 vs 9Improved
restrict to linear mechanisms when conversion parameter p drops to 4two-agent instance · Example 2.1, p=4existence of mechanism incentivizing both agents: 4β1 ≥ 5β2 and 4β2 ≥ 5β1Hurt
use nonlinear monotone mechanism min(F1,F2) instead of lineartwo-agent instance · Example 2.1, p=4existence of mechanism incentivizing both agentsImproved
lower p to 1 (cheating relatively more attractive)two-agent instance · Example 2.1, p=1existence of any monotone mechanism: M(4, 1) > M(1, 4)Hurt
restrict feature count n to a constant when incentivizing all agents to admissible actions with monotone mechanismsProblem 2 · complexitycomputational complexityImproved
switch goal from all agents to maximum number of agents (monotone)Problems 3 and 4 · complexitycomputational complexityHurt
restrict mechanism class from monotone to linear for maximizing incentivized agentsProblems 7 and 8 · complexitycomputational complexityMixed

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