Modeling agent’s preferences by its designer’s social value orientation

ABSTRACT

Human social preferences have been shown to play an important role in many areas of decision-making. There is evidence from the social science literature that human preferences in interpersonal interactions depend partly on a measurable personality trait called, Social Value Orientation (SVO). Automated agents are often written by humans to serve as their delegates when interacting with other agents. Thus, one might expect an agent’s behaviour to be influenced by the SVO of its human designer. With that in mind, we present the following: first, we explore, discuss and provide a solution to the question of how SVO tests that were designed for humans can be used to evaluate agents’ social preferences. Second, we show that in our example domain there is a medium–high positive correlation between the social preferences of agents and their human designers. Third, we exemplify how the SVO information of the designer can be used to improve the performance of some other agents playing against those agents, and lastly, we develop and exemplify the behavioural signature SVO model which allows us to better predict performances when interactions are repeated and behaviour is adapted.

KEYWORDS:

• Agent modelling
• cognitive modelling
• repeated games
• social preference
• social value orientation (SVO)

Notes

No potential conflict of interest was reported by the authors.

1 The remaining 13% could not be classified as having a consistent SVO.

2 The [0, 9] range was selected arbitrarily, and the results in the paper are general for any selected range.

3 The boundary between cooperative and individualistic is . Other boundary angles can be derived similarly.

4 In the next chapter, we further extend the notion of para-SVO by having a special set of tester agents.

5 It skews toward cooperative orientation, possibly because we collected the data from students voluntarily responding to our survey.

6 The ‘equal probability’ assumption is needed to calculate the expect payoff for each action. It can be shown that this assumption is compatible with the para-SVO measurement.

7 SVO of a is measured by testing a with one-shot games, i.e. it is equals to the initial para-SVO of a.