Some dogs can find the payoff-dominant outcome in the Assurance game

Abstract

Studies on coordination often present animals with the choice of either cooperating or remaining inactive; however, in nature, animals may also choose to act alone. This can be modeled with the Assurance game, an economic game that has recently been used to explore decision-making in primates. We investigated whether dyads of pet dogs coordinate in the Assurance game. Pairs were presented with two alternatives: they could individually solve an apparatus baited with a low-value reward (Hare) or they could coordinate to solve a cooperative apparatus baited with a high-value reward for each dog (Stag). All individuals matched their partner's choices, but after controlling for side bias, only four out of eleven dyads consistently coordinated on the payoff-dominant strategy (Stag-Stag). Thus, some dogs are capable of finding coordinated outcomes, as do primates, at least when their partner's actions are visible and coordination results in the biggest payoff for both individuals.

Keywords: Biological sciences; Canine behavior; Cognitive neuroscience; Zoology.

Graphical abstract

Figure 1

Setup for the Assurance game (A–C) Hare table (A), Stag table (B), and starting position (C). In the game trials, subjects can choose whether they want to cooperate (Stag) or defect (Hare) by choosing whether to pull the rope from one or another sliding table. (C) The Stag table is on the left and the Hare table is on the right.

Figure 2

Dyads’ performance in the Assurance game (A) 2D scatterplot showing the proportion of Stag-Stag choices by dyad (excluding trials in which either S1 or S2 did not make a choice), in session 1 (x axis) versus session 2 (y axis). Dyads that showed a majority of Stag-Stag choices in both sessions are shown in green. Dyads that showed a majority of choices of Stag in one session and Hare in the other session (side bias) are shown in purple. The dyad that coordinated on Stag in the first session and made uncoordinated choices in the second session (other) is shown in yellow. (B) Examples of dyads’ performance in the Assurance game. Each dot represents S1’s (black) or S2’s (gray) choice in each trial. Black dots are bigger than gray dots, and thus, when choices overlap and the gray dot is on the top of the black dot, the graph shows the gray dot with a black ring around it. Blank spaces indicate trials in which the individual did not make any choice. For other dyads, see Figures S6–S8.

Figure 3

Relationship between S1 and S2’s choices Proportion of Stag choices of S2 depending on S1’s choice (A) and proportion of Stag choices of S1 depending on S2’s choice in the previous trial (B) (11 dyads). Lines represent the fitted model for the effect of trial number and S1/S2 choices (blue lines represent the predicted response when the other individual choice is Hare; gray lines represent the predicted response if the other individual chooses Stag). Dots represent the proportion of Stag choices of S2 (left) and S1 (right) averaged by session, trial, and whether the other individual choice is Hare (circular points) or Stag (cross-shaped points). Shadowed area corresponds to 95% Wald confidence intervals.