Research map / Learning theory and algorithms / Submodular and game algorithms
Solving Football by Exploiting Equilibrium Structure of 2p0s Differential Games with One-Sided Information
Mukesh Ghimire, Lei Zhang, Zhe Xu, Yi Ren
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add multigrid to CAMS (ablation) | CAMS · 4-stage Hexner's game | runtime (hours): 9.3 hrs -> 2.3 hrs | Improved |
| add multigrid to CAMS (ablation) | CAMS · 10-stage Hexner's game | runtime (hours): 27.6 hrs -> 10.9 hrs | Improved |
| add multigrid to CAMS (ablation) | CAMS · 16-stage Hexner's game | runtime (hours): 46.2 hrs -> 17.8 hrs | Improved |
| use CAMS instead of JPSPG and DeepCFR | 4-stage Hexner's game · 4-stage Hexner's game | wall time / action error: 17 hours for CAMS vs 24 hours for JPSPG, 29 hours (U=9) and 34 hours (U=16) for DeepCFR | Improved |
| increase discrete action set size U from 16 to 144 | CFR+, MMD, CFR-BR-Primal baselines · normal-form Hexner's game | computational cost | Hurt |
| exploit atomic NE structure in model-free MARL (CAMS-DRL vs PPO, MMD) | model-free MARL · 1-stage and 4-stage Hexner's game | policy accuracy vs ground truth | Improved |
Closest papers by meaning
- State-Constrained Zero-Sum Differential Games with One-Sided Information (ICML 2024 · similarity 0.89)
- Team Correlated Equilibria in Zero-Sum Extensive-Form Games via Tree Decompositions (AAAI 2022 · similarity 0.87)
- Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games (NeurIPS 2022 · similarity 0.86)
- Polynomial-Time Computation of Optimal Correlated Equilibria in Two-Player Extensive-Form Games with Public Chance Moves and Beyond (NeurIPS 2020 · similarity 0.86)
- Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games (NeurIPS 2023 · similarity 0.86)
- Bounded Rationality Equilibrium Learning in Mean Field Games (AAAI 2025 · similarity 0.85)
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.
