Automated Explanations for MDP Policies
نویسندگان
چکیده
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. We demonstrate our technique using the problems of advising undergraduate students in their course selection and evaluate it through a user study.
منابع مشابه
Minimal Sufficient Explanations for Factored Markov Decision Processes
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 automat...
متن کاملExplaining recommendations generated by MDPs
There has been little work in explaining recommendations generated by Markov Decision Processes (MDPs). We analyze the difculty of explaining policies computed automatically and identify a set of templates that can be used to generate explanations automatically at run-time. These templates are domain-independent and can be used in any application of an MDP. We show that no additional e ort is r...
متن کاملAn automatic test case generator for evaluating implementation of access control policies
One of the main requirements for providing software security is the enforcement of access control policies which aim to protect resources of the system against unauthorized accesses. Any error in the implementation of such policies may lead to undesirable outcomes. For testing the implementation of access control policies, it is preferred to use automated methods which are faster and more relia...
متن کاملA Natural Language Argumentation Interface for Explanation Generation in Markov Decision Processes
A Markov Decision Process (MDP) policy presents, for each state, an action, which preferably maximizes the expected reward accrual over time. In this paper, we present a novel system that generates, in real time, natural language explanations of the optimal action, recommended by an MDP while the user interacts with the MDP policy. We rely on natural language explanations in order to build trus...
متن کاملInternational Joint Conference on Artificial Intelligence IJCAI
A Markov Decision Process (MDP) policy presents, for each state, an action, which preferably maximizes the expected reward accrual over time. In this paper, we present a novel system that generates, in real time, natural language explanations of the optimal action recommended by an MDP while the user interacts with the MDP policy. We rely on natural language explanations in order to build trust...
متن کامل