Research map / Multi-agent systems and games / Games and equilibria
Efficiently Computing Nash Equilibria in Adversarial Team Markov 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 |
|---|---|---|---|
| Independent policy gradient steps for team players combined with adversary best response (IPGmax) instead of coordinated or centralized team play | IPGmax algorithm for adversarial team Markov games · adversarial team Markov games | computational complexity of computing stationary epsilon-approximate Nash equili | Helped |
| Scaling complexity with sum of team action counts instead of product of team action counts (avoiding treating team as one meta-player) | adversarial team Markov game algorithm · adversarial team Markov games | complexity scaling in number of team actions | Helped |
| Relaxing LP constraints by appropriate slack and phrasing them in terms of the approximate team strategy to guarantee feasibility for the adversary's policy | AdvNashPolicy LP · adversarial team Markov games | feasibility and approximation of Nash equilibrium | No clear effect |
Closest papers by meaning
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · similarity 0.94)
- The Complexity of Two-Team Polymatrix Games with Independent Adversaries (ICLR 2025 · similarity 0.90)
- The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games (NeurIPS 2025 · similarity 0.90)
- Constrained Exploitability Descent: An Offline Reinforcement Learning Method for Finding Mixed-Strategy Nash Equilibrium (ICML 2025 · similarity 0.89)
- Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty Property (AAAI 2024 · similarity 0.89)
- Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games (NeurIPS 2024 · similarity 0.89)
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.