Online Learning in Non-Stationary Markov Decision Processes
published: Aug. 6, 2013, recorded: April 2013, views: 3029
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
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.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !