4 accepted papers
In recent years, significant attention has been directed towards learning average-reward Markov Decision Processes (MDPs). However, existing algorithms either suffer from sub-optimal regret guarantees or computational inefficiencies. In this paper, we present the first *tractable* algorithm with mi…
This paper investigates a new learning problem, the identification of Blackwell optimal policies on deterministic MDPs (DMDPs): A learner has to return a Blackwell optimal policy with fixed confidence using a minimal number of queries. First, we characterize the maximal set of DMDPs for which the id…
In this paper, we examine the long-run behavior of regularized, no-regret learning in finite N-player games. A well-known result in the field states that the empirical frequencies of play under no-regret learning converge to the game’s set of coarse correlated equilibria; however, our understanding…
The first contribution of this paper is the introduction of a new performance measure of a RL algorithm that is more discriminating than the regret, that we call the *regret of exploration* that measures the asymptotic cost of exploration. The second contribution is a new *performance test* (PT) to…