# ScrofaZero: Mastering Trick-taking Poker Game Gongzhu by Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2102.07495 · HTML: https://mlsanity.com/paper/2102.07495/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 15 Feb 2021.

## Builds on (most cited first, 9 of 9)

- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Solving Imperfect-Information Games via Discounted Regret Minimization](https://mlsanity.com/paper/1809.04040/) (2018)
- [Real World Games Look Like Spinning Tops](https://mlsanity.com/paper/2004.09468/) (2020)
- [Monte-Carlo Tree Search as Regularized Policy Optimization](https://mlsanity.com/paper/2007.12509/) (2020)
- [Suphx: Mastering Mahjong with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.13590/) (2020)
- [Differentiable Game Mechanics](https://mlsanity.com/paper/1905.04926/) (2019)
- [On the Impossibility of Global Convergence in Multi-Loss Optimization](https://mlsanity.com/paper/2005.12649/) (2020)
- [Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess](https://mlsanity.com/paper/2009.04374/) (2020)
- [Competitive Bridge Bidding with Deep Neural Networks](https://mlsanity.com/paper/1903.00900/) (2019)

## Abstract (arXiv)

People have made remarkable progress in game AIs, especially in domain of perfect information game. However, trick-taking poker game, as a popular form of imperfect information game, has been regarded as a challenge for a long time. Since trick-taking game requires high level of not only reasoning, but also inference to excel, it can be a new milestone for imperfect information game AI. We study Gongzhu, a trick-taking game analogous to, but slightly simpler than contract bridge. Nonetheless, the strategies of Gongzhu are complex enough for both human and computer players. We train a strong Gongzhu AI ScrofaZero from textittabula rasa by deep reinforcement learning, while few previous efforts on solving trick-taking poker game utilize the representation power of neural networks. Also, we introduce new techniques for imperfect information game including stratified sampling, importance weighting, integral over equivalent class, Bayesian inference, etc. Our AI can achieve human expert level performance. The methodologies in building our program can be easily transferred into a wide range of trick-taking games.