Strategic Teaching and Learning in Games
This reveals fundamental limitations in learning dynamics for game theory, impacting theoretical foundations and applications in economics and AI.
The paper shows that no uncoupled learning heuristic leading to Nash equilibrium in finite games is incentive-compatible, evolutionarily stable, or self-learnable, and players have an incentive to teach opponents to secure at least the Stackelberg leader payoff.
It is known that there are uncoupled learning heuristics leading to Nash equilibrium in all finite games. Why should players use such learning heuristics and where could they come from? We show that there is no uncoupled learning heuristic leading to Nash equilibrium in all finite games that a player has an incentive to adopt, that would be evolutionary stable or that could "learn itself". Rather, a player has an incentive to strategically teach such a learning opponent in order secure at least the Stackelberg leader payoff. The impossibility result remains intact when restricted to the classes of generic games, two-player games, potential games, games with strategic complements or 2x2 games, in which learning is known to be "nice". More generally, it also applies to uncoupled learning heuristics leading to correlated equilibria, rationalizable outcomes, iterated admissible outcomes, or minimal curb sets. A possibility result restricted to "strategically trivial" games fails if some generic games outside this class are considered as well.