We model a Markov decision process, parametrized by an unknown parameter, and study the asymptotic behavior of a sampling-based algorithm, called Thompson sampling. The standard definition of regret is not always suitable to evaluate a policy, especially when the underlying chain structure is general. We show that the standard (expected) regret can grow (super-)linearly and fails to capture the notion of learning in realistic settings with non-trivial state evolution. By decomposing the standard (expected) regret, we develop a new metric, called the expected residual regret, which forgets the immutable consequences of past actions. Instead, it measures regret against the optimal reward moving forward from the current period. We show that the expected residual regret of the Thompson sampling algorithm is upper bounded by a term which converges exponentially fast to 0. We present conditions under which the posterior sampling error of Thompson sampling converges to 0 almost surely. We then introduce the probabilistic version of the expected residual regret and present conditions under which it converges to 0 almost surely. Thus, we provide a viable concept of learning for sampling algorithms which will serve useful in broader settings than had been considered previously.

We consider the problem faced by a service platform that needs to match supply with demand, but also to learn attributes of new arrivals in order to match them better in the future. We introduce a benchmark model with heterogeneous workers and jobs that arrive over time. Job types are known to the platform, but worker types are unknown and must be learned by observing match outcomes. Workers depart after performing a certain number of jobs. The payoff from a match depends on the pair of types and the goal is to maximize the steady-state rate of accumulation of payoff. Our main contribution is a complete characterization of the structure of the optimal policy in the limit that each worker performs many jobs. The platform faces a trade-off for each worker between myopically maximizing payoffs (exploitation) and learning the type of the worker (\emph{exploration}). This creates a multitude of multi-armed bandit problems, one for each worker, coupled together by the constraint on the availability of jobs of different types (capacity constraints). We find that the platform should estimate a shadow price for each job type, and use the payoffs adjusted by these prices, first, to determine its learning goals and then, for each worker, (i) to balance learning with payoffs during the "exploration phase", and (ii) to myopically match after it has achieved its learning goals during the "exploitation phase."