Research map / Multi-agent systems and games / Games and equilibria
The Impact of Exploration on Convergence and Performance of Multi-Agent Q-Learning Dynamics
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 |
|---|---|---|---|
| increase exploration rate T in Q-Learning (smooth Q-learning) | Network Shapley Game · Network Shapley Game (5 agents, beta=0.2) | time-average social welfare (TSW): TSW falls from 3.22 at T=0.1 to 2.0 at T=0.3 | Hurt |
| increase exploration rate T in Q-Learning | Q-Learning dynamics in general network games · Random network games (N=5 to 20) | maximum variation in mixed strategies | Helped |
| increase exploration rate T in Q-Learning | Network Chakraborty Game (15 agents) · Network Chakraborty Game, U=7.0, V=8.5 | TSW | Hurt |
| increase exploration rate T in Q-Learning | Q-Learning dynamics · Theory: network games with unique interior NE | size of convergence neighbourhood (KL set S_T) | Helped |
| increase exploration rate T in Q-Learning | Q-Learning exploitability · Theory: games with unique interior NE | change in exploitability Delta Phi | Helped |
Closest papers by meaning
- Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos (AAAI 2024 · similarity 0.93)
- Asymptotic Extinction in Large Coordination Games (AAAI 2025 · similarity 0.91)
- Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration (NeurIPS 2025 · similarity 0.89)
- Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner's Dilemma (ICML 2025 · similarity 0.88)
- The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration (NeurIPS 2026 · similarity 0.87)
- Synchronization in Learning in Periodic Zero-Sum Games Triggers Divergence from Nash Equilibrium (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.