Deep Learning for Predicting Human Strategic Behavior

99 citations recorded by the source corpus.

How researchers see this paper

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

The Hanabi Challenge: A New Frontier for AI Research (2019, background): “signiﬁcant ﬁnancial support for this work that could have inﬂuenced its outcome.”
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning (2017, background): “A recent work uses a deep learning architecture [34].”
"Other-Play" for Zero-Shot Coordination (2020, methodology): “However, the majority of this research focuses on extremely simple settings such as small normal form games (Wright & Leyton-Brown, 2010; Hartford et al., 2016; Fudenberg & Liang, 2019) or single decision problems (Peysakhovich & Naecker, 2017; Klein-berg et al., 2017) rather than complex…”
Deep Models of Interactions Across Sets (2018, methodology): “First, we introduced a similar parameter-sharing scheme in the context of behavioral game theory (Hartford et al., 2016): rows and columns represented players’ actions and the exchangeable matrix encoded payoffs.”
Predicting In-Game Actions from Interviews of NBA Players (2019, background): “There are some interesting attempts at learning to better predict human action (Erev and Roth 1998; Wright and Leyton-Brown 2010; Hartford, Wright, and Leyton-Brown 2016), but the task at hand is usually addressed in lab conditions or using synthetic data.”