AI Paper Atlas

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

Adaptive and Robust DBSCAN With Multi-Agent Reinforcement Learning

Hao Peng, Xiang Huang, Shuo Sun, Ruitong Zhang, Xizhao Wang, Philip S. Yu

TPAMI 2025 · 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
allocate density partitions to separate agents (AR-DBSCAN vs DRL-DBSCAN)DRL-DBSCAN · 9 offline datasets (average)NMI: .820 -> .891Improved
allocate density partitions to separate agents (AR-DBSCAN vs DRL-DBSCAN)DRL-DBSCAN · 9 offline datasets (average)ARI: .749 -> .826Improved
allocate density partitions to separate agentsDRL-DBSCAN · Pathbased and Cure-t2ARI: underperforms DRL-DBSCAN with 0.041 and 0.071 on the ARI metricHurt
add edge weight normalization (ablation)AR-DBSCAN · PathbasedNMI: 11.9% improvement; .737 -> .825Improved
add one-dimensional structural entropy normalization (ablation)AR-DBSCAN · PathbasedNMI: 5.4% improvement; .783 -> .825Improved
add edge weight normalization (ablation)AR-DBSCAN · Cure-t2NMI: .938 -> .764Hurt
add edge weight normalization (ablation)AR-DBSCAN · D31NMI: .729 -> .773Improved
add H1(G) normalization (ablation)AR-DBSCAN · Cure-t2NMI: .757 -> .764Improved
add DRL parameter search and agents on top of encoding-tree clustering (ablation)Optimal two-level encoding tree · PathbasedNMI: .913 -> .825Hurt
add DRL parameter search and agents on top of encoding-tree clustering (ablation)Optimal two-level encoding tree · AggregationNMI: .836 -> .978Improved
add DRL parameter search and agents on top of encoding-tree clustering (ablation)Optimal two-level encoding tree · Cure-t2NMI: .561 -> .764Improved
use AR-DBSCAN instead of other search baselinesbaseline parameter search · offline datasetsconvergence rounds: converges within 15 rounds and about two times speedupImproved

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