Research map / Multi-agent systems and games / Games and equilibria
A Pair-Approximation Method for Modelling the Dynamics of Multi-Agent Stochastic Games
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 |
|---|---|---|---|
| Track frequencies of agent pairs and their shared state instead of using only mean strategy | Myopic Q-learning in infinite-population stochastic games · Stochastic games | agreement with agent-based simulation | Helped |
| Introduce transitions between SH and PD states | Myopic Q-learning agents · SH↔PD stochastic game | cooperation level | Helped |
| Use deterministic rather than probabilistic state transitions | Myopic Q-learning agents · Two-state PD game | cooperation level | Helped |
| Allow transitions between PD1 and PD2 | Myopic Q-learning agents · Two-state PD game | cooperation level | Mixed |
| Use pair-approximation predictions with small finite populations | Pair-approximation model · SH↔PD stochastic game, n = 10 | prediction agreement with simulation | Mixed |
| Vary the learning rate or exploration temperature | Pair-approximation model · SH↔PD stochastic game | prediction agreement with simulation | No clear effect |
Closest papers by meaning
- Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration (NeurIPS 2025 · similarity 0.91)
- Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos (AAAI 2024 · similarity 0.89)
- Foundations of Multi-Agent Learning in Dynamic Environments: Where Reinforcement Learning Meets Strategic Decision-Making (AAAI 2025 · similarity 0.89)
- Synchronization in Learning in Periodic Zero-Sum Games Triggers Divergence from Nash Equilibrium (AAAI 2025 · similarity 0.88)
- The impact of uncertainty on regularized learning in games (ICML 2025 · similarity 0.88)
- Memory Asymmetry Creates Heteroclinic Orbits to Nash Equilibrium in Learning in Zero-Sum Games (AAAI 2024 · 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.