Material Detail

Online Learning in Non-Stationary Markov Decision Processes

Online Learning in Non-Stationary Markov Decision Processes

This video was recorded at Video Journal of Machine Learning Abstracts - Volume 4. We consider online learning in Markov decision processes with adversarial reward functions. Depending on the information available to the decision maker, we analyze two scenarios: in one setup the stochastic dynamics are known but only the rewards actually received can be observed, while, in the other model, the reward functions are fully observable but the dynamics are unknown and only the actual transitions can be observed. For both cases we present algorithms designed to work under various assumptions on the structure of the state space that enjoy favorable performance guarantees and can be implemented with complexity linear in the problem size.


  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material


Log in to participate in the discussions or sign up if you are not already a MERLOT member.