We introduce AI rationalization, an approach for generating explanations of autonomous system behavior as if a human had performed the behavior. We describe a rationalization technique that uses neural machine translation to translate internal state-action representations of an autonomous agent into natural language. We evaluate our technique in the Frogger game environment, training an autonomous game playing agent to rationalize its action choices using natural language. A natural language training corpus is collected from human players thinking out loud as they play the game. We motivate the use of rationalization as an approach to explanation generation and show the results of two experiments evaluating the effectiveness of rationalization. Results of these evaluations show that neural machine translation is able to accurately generate rationalizations that describe agent behavior, and that rationalizations are more satisfying to humans than other alternative methods of explanation.
|Title of host publication||AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society|
|Number of pages||7|
|State||Published - Dec 27 2018|
|Event||1st AAAI/ACM Conference on AI, Ethics, and Society, AIES 2018 - New Orleans, United States|
Duration: Feb 2 2018 → Feb 3 2018
|Name||AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society|
|Conference||1st AAAI/ACM Conference on AI, Ethics, and Society, AIES 2018|
|Period||2/2/18 → 2/3/18|
Bibliographical noteFunding Information:
This work is supported by ONR N00014-17-1-2373. The views, opinions, and/or conclusions contained in this paper are those of the author and should not be interpreted as representing the official views or policies, either expressed or implied of the ONR or the DoD.
© 2018 ACM.
- ai rationalization
- artificial intelligence
- explainable ai
- machine learning
- user perception
ASJC Scopus subject areas
- Artificial Intelligence