Research map / Multi-agent systems and games / Cooperative multi-agent RL
Emergent Fast-Slow Dynamics in Multi-Agent Q-Learning for Networked Stochastic Games
Yuxin Geng, Wolfram Barfuss, Xingru Chen
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 |
|---|---|---|---|
| make mutual cooperation lead to prosperous state s1 (b1=5) while defection degrades to s2 (b2=1.2) (ablation) | Q-learning agents in stochastic Prisoner's Dilemma · two-state Prisoner's Dilemma | emergence of cooperation: b1 = b2 = 1.2 -> b1 = 5, b2 = 1.2 | Improved |
| raise discount factor so agents value future rewards (gamma = 0.8) (ablation) | Q-learning agents · two-state Prisoner's Dilemma | cooperation: gamma = 0.8 | Improved |
| use learning rate alpha below 10^-3 for time-scale separation (ablation) | FPE theory · two-state Prisoner's Dilemma | agreement between theory and simulation: alpha < 10^-3 | Improved |
| increase graph degree k of random regular graphs (ablation) | networked Q-learning · two-state Prisoner's Dilemma | learning speed | Improved |
Closest papers by meaning
- Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos (AAAI 2024 · similarity 0.90)
- Foundations of Multi-Agent Learning in Dynamic Environments: Where Reinforcement Learning Meets Strategic Decision-Making (AAAI 2025 · similarity 0.89)
- Graph Diffusion for Robust Multi-Agent Coordination (ICML 2025 · similarity 0.89)
- Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective (NeurIPS 2025 · similarity 0.88)
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.88)
- Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems (AAAI 2025 · similarity 0.88)
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.
