Research map / Learning theory and algorithms / Submodular and game algorithms
A Regression Approach for Modeling Games With Many Symmetric Players
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 |
|---|---|---|---|
| GPR with continuous integral expected-payoff estimation instead of deviation-preserving reduction | large symmetric games (33/65/129 players) · random games, 120 instances | expected payoff error | Helped |
| use continuous integral approximation instead of point or neighbor estimation with GPR (ablation) | GPR payoff model · random games, 120 instances | expected payoff error | Helped |
| neighbor estimation instead of point estimation (ablation) | GPR payoff model · random games, 120 instances | expected payoff error | No clear effect |
| over-represent profiles where zero or one players choose a strategy in training data (ablation) | GPR payoff learning · 100-player 3-strategy congestion game | expected payoff error near simplex edges | Helped |
| GPR with integration instead of DPR under noisy payoffs | large symmetric games · 15 action-graph games with noise | regret of computed equilibria | Helped |
| neural network instead of GPR as regressor (point estimate) (ablation) | payoff learning · 100-player 3-strategy congestion game | average expected payoff error | No clear effect |
| more samples per profile for DPR (1 to 20) (ablation) | DPR · noisy action-graph games | error and regret | Mixed |
Closest papers by meaning
- Learning Deviation Payoffs in Simulation-Based Games (AAAI 2019 · similarity 0.91)
- Structure Learning for Approximate Solution of Many-Player Games (AAAI 2020 · similarity 0.91)
- Competing Against Nash Equilibria in Adversarially Changing Zero-Sum Games (ICML 2019 · similarity 0.88)
- Generative Adversarial Equilibrium Solvers (ICLR 2024 · similarity 0.87)
- Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games (ICML 2025 · similarity 0.87)
- Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games (ICML 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.