Unveiling Complex Collective Behaviors from Simple Rewards
Multi-agent Reinforcement Learning (MARL) holds great potential for robot swarms, but the black-box nature of neural policies complicates strategic analysis, limiting multi-robot applications. Furthermore, complex swarm behaviors can surprisingly emerge from simple rewards without explicit aggregation incentives. Unveiling the mechanisms behind this emergence is critical, but the disconnection between simple rewards and collective behaviors exacerbates interpretability challenges. This paper aims to reveal the hidden mechanisms in this process. We propose a two-stage EEC (\LinkIII) explanatory
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 57%jaimasih05-commits/swarm-foraging-qlearn →
- PossiblePossibly related (embedding) · 55%Autonomous navigation of intelligent microrobotic swarms in unknown environments →
- PossiblePossibly related (embedding) · 51%Agentic AI for Robot Teams →
- PossiblePossibly related (embedding) · 51%Shiyao-Huang/awesome-agent-evolution →
- PossiblePossibly related (embedding) · 49%2FastLabs/agent-squad →
- LinkedLinked via arxiv author · 85%Yize Mi →
“Unveiling Complex Collective Behaviors from Simple Rewards”
- LinkedLinked via arxiv author · 85%Jianan Li →
“Unveiling Complex Collective Behaviors from Simple Rewards”
- LinkedLinked via arxiv author · 85%Hongliang Li →
“Unveiling Complex Collective Behaviors from Simple Rewards”