We show 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 a learning opponent to secure at least the Stackelberg leader payoff. This observation holds even when we restrict to generic games, two-player games, potential games, games with strategic complements, or 2 x 2 games, in which learning is known to be "nice." It also applies to uncoupled learning heuristics leading to correlated equilibria, rationalizability, iterated admissibility, or minimal CURB sets.
Schipper, Burkhard C.
"Strategic Teaching and Learning in Games."
American Economic Journal: Microeconomics,
Stochastic and Dynamic Games; Evolutionary Games; Repeated Games
Search; Learning; Information and Knowledge; Communication; Belief; Unawareness