Research map / Multi-agent systems and games / Games and equilibria
Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| set opponents per step m = 0.05n instead of m = n-1 (ablation) | agent-based Q-learning simulation (n=1000) · PD, CS, SH, HD games | agent behaviour (mean Q-value and policy) | No clear effect |
| use the mean field model instead of agent-based simulation | mean field Fokker-Planck model · PD, CS, SH, HD games | expected Q-value trajectory vs mean simulated Q-value | Helped |
| vary the initial Q-value Beta distributions (three cases) (ablation) | mean field model · Stag Hunt | match between model and simulation dynamics | No clear effect |
Closest papers by meaning
- Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos (AAAI 2024 · similarity 0.90)
- Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration (NeurIPS 2025 · similarity 0.90)
- Asymptotic Extinction in Large Coordination Games (AAAI 2025 · similarity 0.88)
- Bounded Rationality Equilibrium Learning in Mean Field Games (AAAI 2025 · similarity 0.88)
- Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner's Dilemma (ICML 2025 · similarity 0.87)
- Foundations of Multi-Agent Learning in Dynamic Environments: Where Reinforcement Learning Meets Strategic Decision-Making (AAAI 2025 · similarity 0.87)
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.