Deep Fictitious Play for Games with Continuous Action Spaces

By Nitin Kamra, Umang Gupta, Kai Wang, Fei Fang, Yan Liu, Milind Tambe. 2019

9 citations recorded by the source corpus.

Fictitious play has been a classic algorithm to solve two-player adversarial games with discrete action spaces. In this work we develop an approximate extension of fictitious play to two-player games with high-dimensional continuous action spaces. We use generative neural networks to approximate players' best responses while also learning a differentiable approximate model to the players' rewards given their actions. Both these networks are trained jointly with gradient-based optimization to emulate fictitious play. We explore our approach in zero-sum games, non zero-sum games and security game domains.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yu Wang
2. Fei Fang
3. Chao Yu
4. Xiaolong Wang
5. Simon Shaolei Du
6. Zhen-Yu Tang
7. Yi Wu
8. Huazhe Xu

In Computer Vision and Pattern Recognition

1. Xiaolong Wang
2. Simon Shaolei Du
3. Yi Wu
4. Huazhe Xu
5. Yu Wang
6. Boyuan Chen
7. Trevor Darrell
8. Luc Van Gool

Citations in the corpus

• Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization (2021, methodology): “…and has attracted increasingly significant interests from AI researchers (Heinrich & Silver, 2016; Lanctot et al., 2017; Foerster et al., 2018; Kamra et al., 2019; Han & Hu, 2019; Bai & Jin, 2020; Perolat et al., 2020): many existing works studied how to design practical multi-agent…”