Johannes Kirschner

  • PhD Student
  • jkirschner@inf.ethz.ch
  • CAB F 65.2
  • +41 44 632 71 44
  • The exploration-exploitation dilemma lies at the core of many machine learning problems: When facing a decision with uncertain outcome, should we try to learn more about the environment or act according to what we believe to be best? I am interested in the theory behind the exploration-exploitation tradeoff in practical relevant settings. In particular I focus on provable good algorithms for the multi-armed bandit problem and more complex reinforcement environments like Markov decision processes. Before joining the group of Andreas Krause I have obtained a Bachelor and Master Degree in Mathematics at ETH Zurich.

Publications

Sorry, no results for this query