AI Paper Atlas

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

System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning

Matteo Bettini, Ajay Shankar, Amanda Prorok

JMLR 2025 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping · 16 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
increase number of equidistant agents n from 2 to 8SND · Goal NavigationSND: 1.51 -> 1.43No clear effect
increase number of equidistant agents n from 2 to 8HSE · Goal NavigationHSE: 1.51 -> 5.21Hurt
increase agents per behavioral cluster from n=2 to n=8 (2 clusters)SND · Goal NavigationSND: 1.49 -> 0.81Improved
increase agents per behavioral cluster from n=2 to n=8 (2 clusters)HSE · Goal NavigationHSE: 1.49 -> 1.91Hurt
constrain SND to 1.33 (optimal) with DiCo versus unconstrained heterogeneousMAPPO · Differential SteeringrewardImproved
constrain SND to too low (0.5) or too high (2) values (ablation)MAPPO with DiCo · Differential SteeringrewardHurt
add one-hot index observation to homogeneous agents (ablation)homogeneous MAPPO · Differential SteeringrewardHurt
use heterogeneous instead of homogeneous policies (ablation)GPPO · Different Size Joint PassagerewardImproved
use heterogeneous instead of homogeneous policies (ablation)GPPO · Asymmetric Payload Joint Passagereward under observation noiseImproved
use heterogeneous instead of homogeneous policies (ablation)GPPO · Asymmetric Payload Joint Passagereward without noiseNo clear effect
use heterogeneous instead of homogeneous policies after wind reintroduced (ablation)GPPO · Flocking in WindrewardImproved
use homogeneous training when SND is about 0 (ablation)IPPO vs HetIPPO · Goal Navigation (1 goal)training timeImproved

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