and they cannot observe other agents' actions or payoffs. Theory shows that even when players have no such information …, simple payoff-based learning rules eventually lead to equilibrium. Such rules have previously been documented for some forms … laboratory setting and finds strong confirmation for key features of payoff-based learning that distinguish it from classical …

Crowd-sourced recommender platforms organize social learning about products by recommending items based on information … study how market structure affects experimentation, social learning, and welfare. I present a model of competing platforms …

learning, choosing among a set of alternative forecasting models. The analysis is accompanied by empirical evidence on the …

Observational learning is typically examined when agents have precise information about their position in the sequence … individuals and receive a private signal about the state of the world. We show that social learning is robust to position … uncertainty. Under any sampling rule satisfying a stationarity assumption, learning is complete if signal strength is unbounded …

product quality. We show that the learning process is successful as long as the price is not prohibitive and therefore at … pricing policy exists. If putting one item on the market involves a constant cost, then under this optimal policy, learning …

Retailers may face uncertainty about the profitability of local markets, which provide opportunities for learning when … retail entry with uncertainty and learning (from others). Using novel data about fast food chains, I estimate the model with … firm beliefs about market profitability. The estimates confirm the presence of uncertainty and learning. Most importantly …

We study observational learning among agents with coordination motives. On a discrete time line, communities of agents … observations are perfectly uncorrelated, asymptotic learning becomes achievable. Herding can also be eliminated by making private …

Information-based reinforcement learning is effective for trading and price discovery in limit order markets. It helps …-run momentum of the informed market orders. The learning increases liquidity supply of uninformed and liquidity consumption of … price discovery. The results shed a light into the market practice of using machine learning in limit order markets …