{"type":"ScholarlyArticle","title":"Model-Free Model Reconciliation","authors":[{"name":"Sarath Sreedharan","slug":"sarath-sreedharan","given":"Sarath","family":"Sreedharan","affiliation":"School of Computing, Informatics, and Decision Systems Engineering , Arizona State University , Tempe , AZ 85281 USA"},{"name":"Alberto Olmo Hernandez","slug":"alberto-olmo-hernandez","given":"Alberto Olmo","family":"Hernandez","affiliation":"School of Computing, Informatics, and Decision Systems Engineering , Arizona State University , Tempe , AZ 85281 USA"},{"name":"Aditya Prasad Mishra","slug":"aditya-prasad-mishra","given":"Aditya Prasad","family":"Mishra","affiliation":"School of Computing, Informatics, and Decision Systems Engineering , Arizona State University , Tempe , AZ 85281 USA"},{"name":"Subbarao Kambhampati","slug":"subbarao-kambhampati","given":"Subbarao","family":"Kambhampati","affiliation":"School of Computing, Informatics, and Decision Systems Engineering , Arizona State University , Tempe , AZ 85281 USA"}],"abstract":"Designing agents capable of explaining complex sequential decisions remains a significant open problem in human-AI interaction. Recently, there has been a lot of interest in developing approaches for generating such explanations for various decision-making paradigms. One such approach has been the idea of explanation as model-reconciliation. The framework hypothesizes that one of the common reasons for a user's confusion could be the mismatch between the user's model of the agent's task model and the model used by the agent to generate the decisions. While this is a general framework, most works that have been explicitly built on this explanatory philosophy have focused on classical planning settings where the model of user's knowledge is available in a declarative form. Our goal in this paper is to adapt the model reconciliation approach to a more general planning paradigm and discuss how such methods could be used when user models are no longer explicitly available. Specifically, we present a simple and easy to learn labeling model that can help an explainer decide what information could help achieve model reconciliation between the user and the agent with in the context of planning with MDPs.","doi":"10.24963/ijcai.2019/83","url":"https://ijcai.org/proceedings/2019/83","pdf":"https://ijcai.org/proceedings/2019/0083.pdf","markdown":"https://ijcai.org/proceedings/2019/83.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/83","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Agent-based and Multi-agent Systems","track":"Main track","number":83,"pages":{"first":587,"last":594},"keywords":["Humans and AI: Human-AI Collaboration","Agent-based and Multi-agent Systems: Human-Agent Interaction"],"videos":[],"references":[{"position":1,"raw":"[Abel, 2019] David Abel. simple rl: Reproducible Rein- forcement Learning in Python. ICLR Workshop on Re- producibility in Machine Learning, 2019.","title":"simple rl: Reproducible Reinforcement Learning in Python","authors":"David Abel, Abel","year":"2019","venue":"ICLR Workshop on Reproducibility in Machine Learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chakraborti and Kambhampati, 2018] Tathagata Chakraborti and Subbarao Kambhampati. (when) can ai bots lie? In AIES, 2018.","title":"when) can ai bots lie? In AIES","authors":"Tathagata Chakraborti, Subbarao Kambhampati","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chakraborti et al., 2017] Tathagata Chakraborti, Sarath Sreedharan, Yu Zhang, and Subbarao Kambhampati. Plan explanations as model reconciliation: Moving beyond explanation as soliloquy. In IJCAI, pages 156-163, 2017.","title":"Plan explanations as model reconciliation: Moving beyond explanation as soliloquy","authors":"Tathagata Chakraborti, Sarath Sreedharan, Yu Zhang, Subbarao Kambhampati","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/23"},{"position":4,"raw":"[Chakraborti et al., 2019] Tathagata Chakraborti, Sarath Sreedharan, and Subbarao Kambhampati. Balancing explicability and explanation in human-aware planning. IJCAI, 2019.","title":"Balancing explicability and explanation in human-aware planning","authors":"Tathagata Chakraborti, Sarath Sreedharan, Subbarao Kambhampati","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Daniele Magazzeni, 2018] Pat Langley Susanne Biundo Daniele Magazzeni, David Smith, editor. Proceedings of the 1st Workshop on Explainable Planning. ICAPS, 2018.","title":"Proceedings of the 1st Workshop on Explainable Planning","authors":null,"year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[David W. Aha and Magazzeni, 2018] Patrick Doherty David W. Aha, Trevor Darrell and Daniele Magazzeni, editors. Proceedings of the 2nd Workshop on Explainable Artificial Intelligence. IJCAI, 2018.","title":"Proceedings of the 2nd Workshop on Explainable Artificial Intelligence","authors":null,"year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dietterich, 1998] Thomas G Dietterich. The maxq method for hierarchical reinforcement learning. In ICML, vol- ume 98, pages 118-126. Citeseer, 1998.","title":"The maxq method for hierarchical reinforcement learning","authors":"G Thomas, Dietterich","year":"1998","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hayes and Shah, 2017] Bradley Hayes and Julie A Shah. Improving robot controller transparency through au- tonomous policy explanation. In 2017 12th ACM/IEEE International Conference on Human-Robot Interaction (HRI), pages 303-312. IEEE, 2017.","title":"Improving robot controller transparency through autonomous policy explanation","authors":"Bradley Hayes, Julie A Shah","year":"2017","venue":"12th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Khan et al., 2009] Omar Zia Khan, Pascal Poupart, and James P Black. Minimal sufficient explanations for fac- tored markov decision processes. In Nineteenth Interna- tional Conference on Automated Planning and Scheduling, 2009.","title":"Minimal sufficient explanations for factored markov decision processes","authors":"Zia Omar, Pascal Khan, James P Poupart, Black","year":"2009","venue":"Nineteenth International Conference on Automated Planning and Scheduling","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kulkarni et al., 2016] Anagha Kulkarni, Tathagata Chakraborti, Yantian Zha, Satya Gautam Vadlamudi, Yu Zhang, and Subbarao Kambhampati. Explicable Robot Planning as Minimizing Distance from Expected Behavior. CoRR, abs/1611.05497, 2016.","title":"Explicable Robot Planning as Minimizing Distance from Expected Behavior","authors":"Anagha Kulkarni, Tathagata Chakraborti, Yantian Zha, Gautam Satya, Yu Vadlamudi, Subbarao Zhang, Kambhampati","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lombrozo, 2006] Tania Lombrozo. The structure and func- tion of explanations. Trends in Cognitive Sciences, 10(10):464 -470, 2006.","title":"The structure and function of explanations","authors":"Tania Lombrozo","year":"2006","venue":"Trends in Cognitive Sciences","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Miller, 2018] Tim Miller. Explanation in artificial intelli- gence: Insights from the social sciences. Artificial Intelli- gence, 2018.","title":"Explanation in artificial intelligence: Insights from the social sciences","authors":"Tim Miller","year":"2018","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Reddy et al., 2018] Siddharth Reddy, Anca D Dragan, and Sergey Levine. Where do you think you're going?: Infer- ring beliefs about dynamics from behavior. NIPS, pages 1454-1465, 2018.","title":"Where do you think you're going?: Inferring beliefs about dynamics from behavior","authors":"Siddharth Reddy, Anca D Dragan, Sergey Levine","year":"2018","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ribeiro et al., 2016] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. Why should i trust you?: Explain- ing the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowl- edge discovery and data mining, pages 1135-1144. ACM, 2016.","title":"Why should i trust you?: Explaining the predictions of any classifier","authors":"Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin","year":"2016","venue":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Russell and Norvig, 2003] Stuart Russell and Peter Norvig. Artificial intelligence: a modern approach. Prentice Hall, 2003.","title":"Artificial intelligence: a modern approach","authors":"Stuart Russell, Peter Norvig","year":"2003","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Seegebarth et al., 2012] Bastian Seegebarth, Felix Müller, Bernd Schattenberg, and Susanne Biundo. Making hybrid plans more clear to human users-a formal approach for generating sound explanations. In Twenty-Second Interna- tional Conference on Automated Planning and Scheduling, 2012.","title":"Making hybrid plans more clear to human users-a formal approach for generating sound explanations","authors":"Bastian Seegebarth, Felix Müller, Bernd Schattenberg, Susanne Biundo","year":"2012","venue":"Twenty-Second International Conference on Automated Planning and Scheduling","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Sreedharan et al., 2018a] Sarath Sreedharan, Subbarao Kambhampati, et al. Handling model uncertainty and multiplicity in explanations via model reconciliation. In Twenty-Eighth International Conference on Automated Planning and Scheduling, pages 518-526, 2018.","title":"Handling model uncertainty and multiplicity in explanations via model reconciliation","authors":"Sreedharan","year":"2018","venue":"Twenty-Eighth International Conference on Automated Planning and Scheduling","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Sreedharan et al., 2018b] Sarath Sreedharan, Siddharth Sri- vastava, and Subbarao Kambhampati. Hierarchical exper- tise level modeling for user specific contrastive explana- tions. In IJCAI, pages 4829-4836, 2018.","title":"Hierarchical expertise level modeling for user specific contrastive explanations","authors":"Sreedharan","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/671"},{"position":19,"raw":"[Sreedharan et al., 2019] Sarath Sreedharan, Tathagata Chakraborti, Christian Muise, and Subbarao Kambham- pati. Planning with Explanatory Actions: A Joint Ap- proach to Plan Explicability and Explanations in Human- Aware Planning. arXiv preprint arXiv:1903.07269, 2019.","title":"Planning with Explanatory Actions: A Joint Approach to Plan Explicability and Explanations in Human-Aware Planning","authors":"Sarath Sreedharan, Tathagata Chakraborti, Christian Muise, Subbarao Kambhampati","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Sutton et al., 1999] Richard S Sutton, Doina Precup, and Satinder Singh. Between mdps and semi-mdps: A frame- work for temporal abstraction in reinforcement learning. Artificial intelligence, 112(1-2):181-211, 1999.","title":"Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning","authors":"Doina Richard S Sutton, Satinder Precup, Singh","year":"1999","venue":"Artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Topin and Veloso, 2019] Nicholay Topin and Manuela Veloso. Generation of policy-level explanations for reinforcement learning. In AAAI, pages 1074-1080, 2019.","title":"Nicholay Topin and Manuela Veloso. Generation of policy-level explanations for reinforcement learning","authors":"Veloso Topin","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zhang et al., 2017] Yu Zhang, Sarath Sreedharan, Anagha Kulkarni, Tathagata Chakraborti, Hankz Hankui Zhuo, and Subbarao Kambhampati. Plan Explicability and Pre- dictability for Robot Task Planning. In ICRA, pages 1313- 1320, 2017.","title":"Plan Explicability and Predictability for Robot Task Planning","authors":"Yu Zhang, Sarath Sreedharan, Anagha Kulkarni, Tathagata Chakraborti, Hankz Hankui Zhuo, Subbarao Kambhampati","year":"2017","venue":"ICRA","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}