3 accepted papers
We consider the problem of navigating in a Markov decision process where extrinsic rewards are either absent or ignored. In this setting, the objective is to learn policies to reach all the states that are reachable within a given number of steps (in expectation) from a starting state. We introduce…
We consider undiscounted reinforcement learning in Markov decision processes (MDPs) where \textit{both} the reward functions and the state-transition probabilities may vary (gradually or abruptly) over time. For this problem setting, we propose an algorithm and provide performance guarantees for th…
We study the K-armed dueling bandit problem which is a variation of the classical Multi-Armed Bandit (MAB) problem in which the learner receives only relative feedback about the selected pairs of arms. We propose a new algorithm called Relative Exponential-weight algorithm for Exploration and Exploi…