Timezone: »

Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs
Andrea Zanette · Emma Brunskill

Wed Jul 11 02:00 AM -- 02:20 AM (PDT) @ A1
In order to make good decision under uncertainty an agent must learn from observations. To do so, two of the most common frameworks are Contextual Bandits and Markov Decision Processes (MDPs). In this paper, we study whether there exist algorithms for the more general framework (MDP) which automatically provide the best performance bounds for the specific problem at hand without user intervention and without modifying the algorithm. In particular, it is found that a very minor variant of a recently proposed reinforcement learning algorithm for MDPs already matches the best possible regret bound $\tilde O (\sqrt{SAT})$ in the dominant term if deployed on a tabular Contextual Bandit problem despite the agent being agnostic to such setting.

Author Information

Andrea Zanette (Stanford University)
Emma Brunskill (Stanford University)
Emma Brunskill

Emma Brunskill is an associate tenured professor in the Computer Science Department at Stanford University. Brunskill’s lab aims to create AI systems that learn from few samples to robustly make good decisions and is part of the Stanford AI Lab, the Stanford Statistical ML group, and AI Safety @Stanford. Brunskill has received a NSF CAREER award, Office of Naval Research Young Investigator Award, a Microsoft Faculty Fellow award and an alumni impact award from the computer science and engineering department at the University of Washington. Brunskill and her lab have received multiple best paper nominations and awards both for their AI and machine learning work (UAI best paper, Reinforcement Learning and Decision Making Symposium best paper twice) and for their work in Ai of education (Intelligent Tutoring Systems Conference, Educational Data Mining conference x3, CHI).

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors