Research map / Learning theory and algorithms / Submodular and game algorithms
A Generalized Training Approach for Multiagent Learning
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 PBR instead of BR | α-PSRO · Randomly generated general-sum games | α-Rank support captured | Helped |
| Use α-Rank instead of exact Nash as the meta-solver | PSRO with BR · Kuhn Poker, 2-player | NashConv convergence | No clear effect |
| Use α-Rank instead of Uniform as the meta-solver | PSRO with BR · Kuhn Poker, 2-player | NashConv convergence | Helped |
| Use α-Rank instead of PRD as the meta-solver | PSRO with BR · Kuhn Poker, more than 2 players | NashConv convergence | No clear effect |
| Use α-Rank instead of PRD as the meta-solver | PSRO with BR · Leduc Poker, 3-player | NashConv convergence | Helped |
| Use α-Rank instead of Uniform as the meta-solver | PSRO with BR · Leduc Poker, 3-player | NashConv convergence | Mixed |
| Use Rectified Nash as the meta-solver | PSRO with BR · Kuhn Poker | NashConv convergence | Hurt |
| Use a novelty-bound PBR oracle (ablation) | α-PSRO · General games | Full convergence to an SSCC | Helped |
| Use PBR instead of BR (ablation) | α-PSRO · Single-population games | Partial convergence to the unique SSCC | Helped |
| Use PBR instead of BR (ablation) | α-PSRO · Multi-population games | Partial convergence to an SSCC | Mixed |
| Use α-Rank instead of Nash as the meta-solver | PSRO · MuJoCo soccer | Feasibility with reinforcement-learning oracles | No clear effect |
Closest papers by meaning
- XDO: A Double Oracle Algorithm for Extensive-Form Games (NeurIPS 2021 · similarity 0.91)
- Toward Optimal Policy Population Growth in Two-Player Zero-Sum Games (ICLR 2024 · similarity 0.91)
- Global Policy-Space Response Oracles for Two-Player Zero-Sum Games (ICML 2026 · similarity 0.91)
- A-PSRO: A Unified Strategy Learning Method with Advantage Metric for Normal-form Games (ICML 2025 · similarity 0.91)
- Efficient Learning in Polyhedral Games via Best-Response Oracles (AAAI 2024 · similarity 0.88)
- No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests (NeurIPS 2024 · similarity 0.88)
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.