Research map / Multi-agent systems and games / Games and equilibria
Exponential Lower Bounds for Fictitious Play in Potential 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 |
|---|---|---|---|
| Use the recursively constructed payoff matrix K^n(0), starting from (n,1) | Fictitious Play · Two-player identical-payoff game | rounds to ε-approximate NE: Ω\left(4^n ((n/2-2)!)^4 + \frac{1}{n\sqrt{\epsilon}} \right) | Hurt |
| Use the recursively constructed payoff matrix K^n(0) | Fictitious Play with uniformly random initialization · Two-player identical-payoff game | expected rounds to ε-approximate NE: Ω\left( \frac{4^n ((n/2-2)!)^4 + 1/n\sqrt{\epsilon}}{n^2}\right) | Hurt |
| Apply any tie-breaking rule rather than an adversarially selected one | Fictitious Play on K^n(0) · Two-player identical-payoff game | rounds to reach the target strategy profile | No clear effect |
Closest papers by meaning
- Smooth Fictitious Play in Stochastic Games with Perturbed Payoffs and Unknown Transitions (NeurIPS 2022 · similarity 0.90)
- Fictitious Play and Best-Response Dynamics in Identical Interest and Zero-Sum Stochastic Games (ICML 2022 · similarity 0.90)
- Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications (NeurIPS 2020 · similarity 0.89)
- Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions (ICML 2021 · similarity 0.88)
- Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games (NeurIPS 2024 · similarity 0.87)
- Can Reinforcement Learning Solve Asymmetric Combinatorial-Continuous Zero-Sum Games? (ICLR 2025 · 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.