The optimistic principle for online planning in Markov decision processes
published: May 28, 2013, recorded: September 2012, views: 2632
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.
Given an initial state, what is the best possible action that can be returned by a planning algorithm that is given a finite numerical budget (e.g. number of calls to a model of the state-transition and reward functions). We investigate optimistic strategies and provide regret bounds in terms of a new measure of the complexity of the planning problem.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !