Game theory, argumentation and dialogues all address problems
concerning inter-agent interaction, but from different perspectives.
In this paper, we contribute to the study of the interplay between
these fields. In particular, we show that by mapping games in normal
form into structured argumentation, computing dominant solutions
and Nash equilibria is equivalent to computing admissible
sets of arguments. Moreover, when agents lack complete information,
computing dominant solutions/Nash equilibria is equivalent
to constructing successful (argumentation-based) dialogues.
Finally, we study agents’ behaviour in these dialogues in reverse
game-theoretic terms and show that, using specific notions of utility,
agents engaged in (argumentation-based) dialogues are guaranteed
to be truthful and disclose relevant information, and thus
can converge to dominant solutions/Nash equilibria of the original
games even under incomplete information.