AAAI Publications, Nineteenth International Conference on Automated Planning and Scheduling

Font Size: 
Minimal Sufficient Explanations for Factored Markov Decision Processes
Omar Zia Khan, Pascal Poupart, James P. Black

Last modified: 2009-10-16


Explaining policies of Markov Decision Processes (MDPs) is complicated due to their probabilistic and sequential nature. We present a technique to explain policies for factored MDP by populating a set of domain-independent templates. We also present a mechanism to determine a minimal set of templates that, viewed together, completely justify the policy. Our explanations can be generated automatically at run-time with no additional effort required from the MDP designer. We demonstrate our technique using the problems of advising undergraduate students in their course selection and assisting people with dementia in completing the task of handwashing. We also evaluate our explanations for course-advising through a user study involving students.


Policy Explanation; Markov Decision Processes

Full Text: PDF