# A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solving

arXiv: https://arxiv.org/abs/2206.09161 · HTML: https://mlsanity.com/paper/2206.09161/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 39 references that are in the map.
- First posted on arXiv 18 Jun 2022.

## Builds on (most cited first, 15 of 15)

- [DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker](https://mlsanity.com/paper/1701.01724/) (2017)
- [OpenSpiel: A Framework for Reinforcement Learning in Games](https://mlsanity.com/paper/1908.09453/) (2019)
- [Solving Large Imperfect Information Games Using CFR+](https://mlsanity.com/paper/1407.5042/) (2014)
- [Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1811.01458/) (2018)
- [Safe and Nested Subgame Solving for Imperfect-Information Games](https://mlsanity.com/paper/1705.02955/) (2017)
- [Depth-Limited Solving for Imperfect-Information Games](https://mlsanity.com/paper/1805.08195/) (2018)
- [Computational Results for Extensive-Form Adversarial Team Games](https://mlsanity.com/paper/1711.06930/) (2017)
- [No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium](https://mlsanity.com/paper/2004.00603/) (2020)
- [Solving Common-Payoff Games with Approximate Policy Iteration](https://mlsanity.com/paper/2101.04237/) (2021)
- [Team-maxmin equilibrium: efficiency bounds and algorithms](https://mlsanity.com/paper/1611.06134/) (2016)
- [Team Correlated Equilibria in Zero-Sum Extensive-Form Games via Tree Decompositions](https://mlsanity.com/paper/2109.05284/) (2021)
- [Coordination in Adversarial Sequential Team Games via Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/1912.07712/) (2019)
- [Computing Ex Ante Coordinated Team-Maxmin Equilibria in Zero-Sum Multiplayer Extensive-Form Games](https://mlsanity.com/paper/2009.12629/) (2020)
- [Sparsified Linear Programming for Zero-Sum Equilibrium Finding](https://mlsanity.com/paper/2006.03451/) (2020)
- [Multi-Agent Coordination in Adversarial Environments through Signal Mediated Strategies](https://mlsanity.com/paper/2102.05026/) (2021)

## Built on by (most cited first, 7 of 7)

- [Efficiently Computing Nash Equilibria in Adversarial Team Markov Games](https://mlsanity.com/paper/2208.02204/) (2022)
- [Abstracting Imperfect Information Away from Two-Player Zero-Sum Games](https://mlsanity.com/paper/2301.09159/) (2023)
- [Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem](https://mlsanity.com/paper/2410.05673/) (2024)
- [The Update-Equivalence Framework for Decision-Time Planning](https://mlsanity.com/paper/2304.13138/) (2023)
- [GraphChase: A Platform and Benchmark for Urban Network Security Games](https://mlsanity.com/paper/2501.17559/) (2025)
- [Computing Ex Ante Equilibrium in Heterogeneous Zero-Sum Team Games](https://mlsanity.com/paper/2410.01575/) (2024)
- [Beyond Bayesian Nash: Learning Minimax-Regret Equilibria for Adversarial Team Games under Asymmetric Information](https://mlsanity.com/paper/2607.09993/) (2026)

## Abstract (arXiv)

Ex ante correlation is becoming the mainstream approach for sequential adversarial team games, where a team of players faces another team in a zero-sum game. It is known that team members' asymmetric information makes both equilibrium computation textsfAPX-hard and team's strategies not directly representable on the game tree. This latter issue prevents the adoption of successful tools for huge 2-player zero-sum games such as, e.g., abstractions, no-regret learning, and subgame solving. This work shows that we can recover from this weakness by bridging the gap between sequential adversarial team games and 2-player games. In particular, we propose a new, suitable game representation that we call team-public-information, in which a team is represented as a single coordinator who only knows information common to the whole team and prescribes to each member an action for any possible private state. The resulting representation is highly explainable, being a 2-player tree in which the team's strategies are behavioral with a direct interpretation and more expressive than the original extensive form when designing abstractions. Furthermore, we prove payoff equivalence of our representation, and we provide techniques that, starting directly from the extensive form, generate dramatically more compact representations without information loss. Finally, we experimentally evaluate our techniques when applied to a standard testbed, comparing their performance with the current state of the art.