Sequential Naive Learning
This research provides a theoretical condition for asymptotic learning in sequential decision-making for agents with bounded rationality, which is relevant for understanding collective behavior in social and economic systems.
This paper analyzes how boundedly rational agents update their beliefs and actions sequentially based on aggregate statistics. It finds that asymptotic learning occurs if and only if agents use a probability matching decision rule, even when information structures vary across agents or there are multiple states and actions.
We analyze boundedly rational updating from aggregate statistics in a model with binary actions and binary states. Agents each take an irreversible action in sequence after observing the unordered set of previous actions. Each agent first forms her prior based on the aggregate statistic, then incorporates her signal with the prior based on Bayes rule, and finally applies a decision rule that assigns a (mixed) action to each belief. If priors are formed according to a discretized DeGroot rule, then actions converge to the state (in probability), i.e., \emph{asymptotic learning}, in any informative information structure if and only if the decision rule satisfies probability matching. This result generalizes to unspecified information settings where information structures differ across agents and agents know only the information structure generating their own signal. Also, the main result extends to the case of $n$ states and $n$ actions.