Research map / Multi-agent systems and games / Games and equilibria
Team-PSRO for Learning Approximate TMECor in Large Team Games via Cooperative Reinforcement Learning
Stephen Marcus McAleer, Gabriele Farina, Gaoyue Zhou, Mingzhi Wang, Yaodong Yang, Tuomas Sandholm
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 mix-and-match (evaluate payoffs of mixed joint strategies) to Team DO (ablation) | Team DO · 4-player Kuhn poker and Liar's dice | exploitability vs number of best response computations | Improved |
| Add mix-and-match to Team DO, measured in wall clock time on small games (ablation) | Team DO · Kuhn poker and Liar's dice | wall clock convergence | Hurt |
| Use Team DO instead of Fictitious Team Play | Tabular team games · Kuhn poker and Liar's dice | exploitability | Improved |
| Use Team PSRO instead of self-play MAPPO | MAPPO · Google Research Football, imperfect information | Elo, goal difference vs AI, relative population performance | Improved |
| Add mix-and-match to Team PSRO (ablation) | Team PSRO · Google Research Football | Elo, goal difference, RPP | Improved |
| Use perfect-information observations instead of imperfect | Team PSRO · Google Research Football | ranking of methods | No clear effect |
| Increase training timesteps | Team PSRO-MM vs Team PSRO · Google Research Football, score vs self-play | average score x100 | Mixed |
| Use Team PSRO instead of fictitious play and prioritized fictitious self play | Team best-response baselines · Google Research Football | Elo and head-to-head | Improved |
Closest papers by meaning
- Learning Global Nash Equilibrium in Team Competitive Games with Generalized Fictitious Cross-Play (JMLR 2025 · similarity 0.88)
- A Generalized Training Approach for Multiagent Learning (ICLR 2020 · similarity 0.88)
- Neural Auto-Curricula in Two-Player Zero-Sum Games (NeurIPS 2021 · similarity 0.87)
- Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games (NeurIPS 2024 · similarity 0.87)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · similarity 0.86)
- Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games (ICML 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.
