Learning to cooperate in multi-agent social dilemmas

59 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.

Multi-agent Reinforcement Learning in Sequential Social Dilemmas (2017, background): “Our main result is that both of the SSDs we considered, Gathering and Wolfpack, have empirical payoﬀ matrices that are Prisoner’s Dilemma (PD).”
The world of independent learners is not markovian (2011, background): “All the recent surveys and many works on multiagent learning mention this fact as a key challenge [5, 35, 21, 24, 38, 10, 6, 32, 39, 26, 13, 40].”
Multi-agent deep reinforcement learning: a survey (2021, background): “Social dilemmas have long been studied as conflict scenario in which agents gauge between individualistic and collective profits (Crandall and Goodrich 2011; De Cote et al. 2006).”
Inequity aversion improves cooperation in intertemporal social dilemmas (2018, methodology): “oposed inﬂuential models based on behavioral game theory. However, these models have limited applicability since they only generate predictions when the problem can be cast as a matrix game (see e.g. [12, 13]). Here we consider a more realistic video-game setting, like those introduced in the behavi”