Home   Research Publications Members Related Software
IndexBrowse   BibliographiesMy selection
 Search: in   (word length ≥ 3)
Publication no #629   Download bibtex file Type :   Html | Bib | Both
Add to my selection
Tradeoff-Focused Contrastive Explanation for MDP Planning

Roykrong Sukkerd, Reid Simmons and David Garlan.

In Proceedings of the The 29th IEEE International Conference on Robot & Human Interactive Communication, Virtual, 31 August - 4 September 2020. To appear.

Online links: PDF   Bibtex entry   Plain Text

End-users’ trust in automated agents is important as automated decision-making and planning is increasingly used in many aspects of people’s lives. In real-world applications of planning, multiple optimization objectives are often involved.Thus, planning agents’ decisions can involve complex tradeoffs among competing objectives. It can be difficult for the end-users to understand why an agent decides on a particular planning solution on the basis of its objective values. As a result, the users may not know whether the agent is making the right decisions, and may lack trust in it. In this work, we contribute an approach, based on contrastive explanation, that enables a multi-objective MDP planning agent to explain its decisions in a way that communicates its tradeoff rationale in terms of the domain-level concepts. We conduct a human subjects experiment to evaluate the effectiveness of our explanation approach in a mobile robot navigation domain. The results show that our approach significantly improves the users’ understanding, and confidence in their understanding, of the tradeoff rationale of the planning agent

Keywords: Explainable Software, Planning.  
    Created: 2020-05-08 14:39:47     Modified: 2020-07-06 12:47:17
Feedback: ABLE Webmaster
Last modified: Sat October 12 2019 16:15:32