{"type":"ScholarlyArticle","title":"Incorporating Failure Events in Agents’ Decision Making to Improve User Satisfaction","authors":[{"name":"David Sarne","slug":"david-sarne","given":"David","family":"Sarne","affiliation":"Department of Computer Science , Bar-Ilan University , Israel"},{"name":"Chen Rozenshtein","slug":"chen-rozenshtein","given":"Chen","family":"Rozenshtein","affiliation":"Department of Computer Science , Bar-Ilan University , Israel"}],"abstract":"This paper suggests a new paradigm for the design of collaborative autonomous agents engaged in executing a joint task alongside a human user.  In particular, we focus on the way an agent's failures should affect its decision making, as far as user satisfaction measures are concerned.  Unlike the common practice that considers agent (and more broadly, system) failures solely in the prism of their influence over the agent's contribution to the execution of the joint task, we argue that there is an additional, direct, influence which cannot be fully captured by the above measure. Through two series of large-scale controlled experiments with 450 human subjects, recruited through Amazon Mechanical Turk, we show that, indeed, such direct influence holds. Furthermore, we show that the use of a simple agent design that takes into account the direct influence of failures in its decision making yields considerably better user satisfaction, compared to an agent that focuses exclusively on maximizing its absolute contribution to the joint task.","doi":"10.24963/ijcai.2020/215","url":"https://ijcai.org/proceedings/2020/215","pdf":"https://ijcai.org/proceedings/2020/0215.pdf","markdown":"https://ijcai.org/proceedings/2020/215.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/215","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Humans and AI","track":"Main track","number":215,"pages":{"first":1549,"last":1555},"keywords":["Robotics: Human Robot Interaction","Humans and AI: Human-AI Collaboration","Humans and AI: Human-Computer Interaction"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24865/file_24865.m3u8","length_sec":295,"provider":"hls"}],"references":[{"position":1,"raw":"[Alkoby et al., 2019] Shani Alkoby, Avilash Rath, and Peter Stone. Teaching social behavior through human reinforce- ment for ad hoc teamwork-the star framework. In Proceed- ings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, pages 1773-1775, 2019.","title":"Teaching social behavior through human reinforcement for ad hoc teamwork-the star framework","authors":"Shani Alkoby, Avilash Rath, Peter Stone","year":"2019","venue":"Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Altshuler and Sarne, 2018] Nadav Kiril Altshuler and David Sarne. Modeling assistant's autonomy constraints as a means for improving autonomous assistant-agent de- sign. In Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, pages 1468-1476, 2018.","title":"Modeling assistant's autonomy constraints as a means for improving autonomous assistant-agent design","authors":"Sarne ; Altshuler, Kiril Nadav, David Altshuler, Sarne","year":"2018","venue":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cohen and Sarne, 2018] Guy Cohen and David Sarne. Tim- ing rating requests for maximizing obtained rating. In Proceedings of the 17th International Conference on Au- tonomous Agents and MultiAgent Systems, pages 1906- 1908, 2018.","title":"Timing rating requests for maximizing obtained rating","authors":"Sarne Cohen, Guy Cohen, David Sarne","year":"2018","venue":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Correia et al., 2018] Filipa Correia, Carla Guerra, Samuel Mascarenhas, Francisco S Melo, and Ana Paiva. Explor- ing the impact of fault justification in human-robot trust. In Proceedings of the 17th International Conference on Au- tonomous Agents and MultiAgent Systems, pages 507-513, 2018.","title":"Exploring the impact of fault justification in human-robot trust","authors":"Filipa Correia, Carla Guerra, Samuel Mascarenhas, Francisco S Melo, Ana Paiva","year":"2018","venue":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Dabholkar and Spaid, 2012] Pratibha A Dabholkar and Brian I Spaid. Service failure and recovery in using technology-based self-service: effects on user attribu- tions and satisfaction. The Service Industries Journal, 32(9):1415-1432, 2012.","title":"Service failure and recovery in using technology-based self-service: effects on user attributions and satisfaction","authors":"A Pratibha, Brian I Dabholkar, Spaid","year":"2012","venue":"The Service Industries Journal","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Elmalech et al., 2015] Avshalom Elmalech, David Sarne, Avi Rosenfeld, and Eden Shalom Erez. When subopti- mal rules. In Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015.","title":"When suboptimal rules","authors":"Avshalom Elmalech, David Sarne, Avi Rosenfeld, Eden Shalom, Erez","year":"2015","venue":"Twenty-Ninth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gelderman, 1998] Maarten Gelderman. The relation be- tween user satisfaction, usage of information systems and performance. Info. & management, 34(1):11-18, 1998.","title":"The relation between user satisfaction, usage of information systems and performance","authors":"Maarten Gelderman, Gelderman","year":"1998","venue":"Info. & management","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gompei and Umemuro, 2015] Takayuki Gompei and Hi- royuki Umemuro. A robot's slip of the tongue: Effect of speech error on the familiarity of a humanoid robot. In 2015 24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), pages 331-336. IEEE, 2015.","title":"Takayuki Gompei and Hiroyuki Umemuro. A robot's slip of the tongue: Effect of speech error on the familiarity of a humanoid robot","authors":"Umemuro Gompei","year":"2015","venue":"24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Honig and Oron-Gilad, 2018] Shanee Sarah Honig and Tal Oron-Gilad. Understanding and resolving failures in human-robot interaction: Literature review and model de- velopment. Frontiers in psychology, 9:861, 2018.","title":"Understanding and resolving failures in human-robot interaction: Literature review and model development","authors":"Sarah Shanee, Tal Honig, Oron-Gilad","year":"2018","venue":"Frontiers in psychology","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kahneman, 2000] Daniel Kahneman. A psychological point of view: Violations of rational rules as a diagnostic of mental processes. Behavioral and Brain Sciences, 23(5):681-683, 2000.","title":"A psychological point of view: Violations of rational rules as a diagnostic of mental processes","authors":"Daniel Kahneman","year":"2000","venue":"Behavioral and Brain Sciences","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kwon et al., 2018] Minae Kwon, Sandy H Huang, and Anca D Dragan. Expressing robot incapability. In Pro- ceedings of the 2018 ACM/IEEE International Conference on Human-Robot Interaction, pages 87-95. ACM, 2018.","title":"Expressing robot incapability","authors":"Minae Kwon, Sandy H Huang, Anca D Dragan","year":"2018","venue":"Proceedings of the 2018 ACM/IEEE International Conference on Human-Robot Interaction","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Levy and Sarne, 2016] Priel Levy and David Sarne. Intelli- gent advice provisioning for repeated interaction. In Thir- tieth AAAI Conference on Artificial Intelligence, 2016.","title":"Intelligent advice provisioning for repeated interaction","authors":"Sarne ; Levy, Priel Levy, David Sarne","year":"2016","venue":"Thirtieth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lucas et al., 2017] Gale M Lucas, Jill Boberg, David Traum, Ron Artstein, Jon Gratch, Alesia Gainer, Em- manuel Johnson, Anton Leuski, and Mikio Nakano. The role of social dialogue and errors in robots. In Proceed- ings of the 5th International Conference on Human Agent Interaction, pages 431-433. ACM, 2017.","title":"The role of social dialogue and errors in robots","authors":"Lucas","year":"2017","venue":"Proceedings of the 5th International Conference on Human Agent Interaction","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Mirnig et al., 2017] Nicole Mirnig, Gerald Stollnberger, Markus Miksch, Susanne Stadler, Manuel Giuliani, and Manfred Tscheligi. To err is robot: how humans assess and act toward an erroneous social robot. Frontiers, 4(21):1, 2017.","title":"To err is robot: how humans assess and act toward an erroneous social robot","authors":"Nicole Mirnig, Gerald Stollnberger, Markus Miksch, Susanne Stadler, Manuel Giuliani, Manfred Tscheligi","year":"2017","venue":"Frontiers","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ramchurn et al., 2016] Sarvapali D Ramchurn, Feng Wu, Wenchao Jiang, Joel E Fischer, Steve Reece, Stephen Roberts, Tom Rodden, Chris Greenhalgh, and Nicholas R Jennings. Human-agent collaboration for disaster re- sponse. Autonomous Agents and Multi-Agent Systems, 30(1):82-111, 2016.","title":"Human-agent collaboration for disaster response","authors":"Feng Sarvapali D Ramchurn, Wenchao Wu, Joel E Jiang, Steve Fischer, Stephen Reece, Tom Roberts, Chris Rodden, Nicholas R Greenhalgh, Jennings","year":"2016","venue":"Autonomous Agents and Multi-Agent Systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Robinette et al., 2015] Paul Robinette, Ayanna M Howard, and Alan R Wagner. Timing is key for robot trust repair. In International Conference on Social Robotics, pages 574- 583. Springer, 2015.","title":"Timing is key for robot trust repair","authors":"Paul Robinette, Ayanna M Howard, Alan R Wagner","year":"2015","venue":"International Conference on Social Robotics","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Salem et al., 2013] Maha Salem, Friederike Eyssel, Katha- rina Rohlfing, Stefan Kopp, and Frank Joublin. To err is human (-like): Effects of robot gesture on perceived an- thropomorphism and likability. International Journal of Social Robotics, 5(3):313-323, 2013.","title":"To err is human (-like): Effects of robot gesture on perceived anthropomorphism and likability","authors":"Maha Salem, Friederike Eyssel, Katharina Rohlfing, Stefan Kopp, Frank Joublin","year":"2013","venue":"International Journal of Social Robotics","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Salem et al., 2015] Maha Salem, Gabriella Lakatos, Farshid Amirabdollahian, and Kerstin Dautenhahn. Would you trust a (faulty) robot?: Effects of error, task type and per- sonality on human-robot cooperation and trust. In Pro- ceedings of the Tenth International Conference on Human- Robot Interaction, pages 141-148. ACM, 2015.","title":"Would you trust a (faulty) robot?: Effects of error, task type and personality on human-robot cooperation and trust","authors":"Maha Salem, Gabriella Lakatos, Farshid Amirabdollahian, Kerstin Dautenhahn","year":"2015","venue":"Proceedings of the Tenth International Conference on Human-Robot Interaction","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Short et al., 2010] Elaine Short, Justin Hart, Michelle Vu, and Brian Scassellati. No fair!! an interaction with a cheating robot. In ACM/IEEE International Conference on Human-Robot Interaction (HRI), pages 219-226, 2010.","title":"No fair!! an interaction with a cheating robot","authors":"Elaine Short, Justin Hart, Michelle Vu, Brian Scassellati","year":"2010","venue":"ACM/IEEE International Conference on Human-Robot Interaction (HRI)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Vaidya et al., 2018] Tushar Vaidya, Carlos Murguia, and Georgios Piliouras. Learning agents in financial markets: Consensus dynamics on volatility. In Proceedings of the 17th AAMAS, pages 2106-2108, 2018.","title":"Learning agents in financial markets: Consensus dynamics on volatility","authors":"Tushar Vaidya, Carlos Murguia, Georgios Piliouras","year":"2018","venue":"Proceedings of the 17th AAMAS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[van der Woerdt and Haselager, 2016] Sophie van der Wo- erdt and Pim Haselager. Lack of effort or lack of ability? robot failures and human perception of agency and respon- sibility. In Benelux Conference on Artificial Intelligence, pages 155-168. Springer, 2016.","title":"Sophie van der Woerdt and Pim Haselager. Lack of effort or lack of ability? robot failures and human perception of agency and responsibility","authors":"Van Der Woerdt, Haselager","year":"2016","venue":"Benelux Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[van Wissen et al., 2012] Arlette van Wissen, Ya'akov Gal, BA Kamphorst, and MV Dignum. Human-agent team- work in dynamic environments. Computers in Human Be- havior, 28(1):23-33, 2012.","title":"Human-agent teamwork in dynamic environments","authors":"Van Wissen","year":"2012","venue":"Computers in Human Behavior","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2013] Yuqiong Wang, Peter Khooshabeh, and Jonathan Gratch. Looking real and making mistakes. In In- ternational Workshop on Intelligent Virtual Agents, pages 339-348. Springer, 2013.","title":"Looking real and making mistakes","authors":"Wang","year":"2013","venue":"International Workshop on Intelligent Virtual Agents","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}