Research map / Multi-agent systems and games / Games and equilibria
Dynamic Evolution of Complex Networks: A Reinforcement Learning Approach Applying Evolutionary Games to Community Structure
Bin Pi, Liang-Jian Deng, Minyu Feng, Matjaž Perc, Jürgen Kurths
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace the heuristic explore-and-move rule with Q-learning agents (ablation) | SWOBD · community structure on 2D grid | community stability / degree distribution | Improved |
| raise learning rate from 0.1 to 0.9 | SWOBD · community formation, N_c | time to steady state: t=6,000 -> t=3,000 | Improved |
| raise learning rate from 0.2 to 0.7 | SWOBD · community formation, N_c | time to steady state: t=5,000 -> t=3,000 | Improved |
| use large discount factor (0.7-0.9) instead of small (0.1-0.2) | SWOBD · community formation, N_c | N_c stability: fluctuations, ultimately reducing to approximately 50 | Hurt |
| increase grid rows and columns from (4, 4) to (13, 13) | SWOBD · number of communities | number of communities: 1 -> 5 | Improved |
| use different death distributions (power-law, uniform, exponential, lognormal) | SWBD · stationary population size | relative error: 1.569% , 0.699%, 0.571%, 1.412% | No clear effect |
Closest papers by meaning
- Emergent Fast-Slow Dynamics in Multi-Agent Q-Learning for Networked Stochastic Games (AAAI 2026 · similarity 0.90)
- Complex Network Evolution Model Based on Turing Pattern Dynamics (TPAMI 2022 · similarity 0.89)
- Tapes Together Strong: The Co-evolution of Computation and Cooperation (NeurIPS 2026 · similarity 0.88)
- Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos (AAAI 2024 · similarity 0.87)
- Evolutionary Prediction Games (NeurIPS 2025 · similarity 0.86)
- Online Control in Population Dynamics (NeurIPS 2024 · similarity 0.86)
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.
