{"type":"ScholarlyArticle","title":"Sample Efficient Paradigms for Personalized Assessment of Taskable AI Systems","authors":[{"name":"Pulkit Verma","slug":"pulkit-verma","given":"Pulkit","family":"Verma","affiliation":"Autonomous Agents and Intelligent Robots Lab , School of Computing and Augmented Intelligence , Arizona State University , USA"}],"abstract":"The vast diversity of internal designs of taskable black-box AI systems and their nuanced zones of safe functionality make it difficult for a layperson to use them without unintended side effects. The focus of my dissertation is to develop paradigms that would enable a user to assess and understand the limits of an AI system's safe operability. We develop a personalized AI assessment module that lets an AI system execute instruction sequences in simulators and answer queries about these executions. Our results show that such a primitive query-response capability is sufficient to efficiently derive a user-interpretable model of the system's capabilities in fully observable settings.","doi":"10.24963/ijcai.2023/824","url":"https://ijcai.org/proceedings/2023/824","pdf":"https://ijcai.org/proceedings/2023/0824.pdf","markdown":"https://ijcai.org/proceedings/2023/824.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/824","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Doctoral Consortium","track":"Doctoral Consortium","number":824,"pages":{"first":7099,"last":7100},"keywords":["Planning and Scheduling: PS: Learning in planning and scheduling","Knowledge Representation and Reasoning: KRR: Learning and reasoning","Planning and Scheduling: PS: Model-based reasoning","Knowledge Representation and Reasoning: KRR: Reasoning about actions"],"videos":[],"references":[{"position":1,"raw":"[Aineto et al., 2019] D. Aineto, S. J. Celorrio, and E. Onaindia. Learning action models with minimal observability. Artificial In- telligence, 275:104-137, 2019.","title":"Learning action models with minimal observability","authors":"D Aineto, S J Celorrio, E Onaindia","year":"2019","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Arora et al., 2018] A. Arora, H. Fiorino, D. Pellier, M. Métivier, and S. Pesty. A review of learning planning action models. Knowledge Engineering Review, 33:E20, 2018.","title":"A review of learning planning action models","authors":"A Arora, H Fiorino, D Pellier, M Métivier, S Pesty","year":"2018","venue":"Knowledge Engineering Review","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chakraborti et al., 2017] T. Chakraborti, S. Sreedharan, Y. Zhang, and S. Kambhampati. Plan explanations as model reconciliation: Moving beyond explanation as soliloquy. In IJCAI, 2017.","title":"Plan explanations as model reconciliation: Moving beyond explanation as soliloquy","authors":"T Chakraborti, S Sreedharan, Y Zhang, S Kambhampati","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/23"},{"position":4,"raw":"[Chitnis et al., 2021] R. Chitnis, T. Silver, J. Tenenbaum, L. P. Kaelbling, and T. Lozano-Pérez. GLIB: Efficient exploration for relational model-based reinforcement learning via goal-literal babbling. In AAAI, 2021.","title":"GLIB: Efficient exploration for relational model-based reinforcement learning via goal-literal babbling","authors":"R Chitnis, T Silver, J Tenenbaum, L P Kaelbling, T Lozano-Pérez","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Nayyar et al., 2022] R. K. Nayyar, P. Verma, and S. Srivastava. Differential assessment of black-box AI agents. In AAAI, 2022.","title":"Differential assessment of black-box AI agents","authors":"R K Nayyar, P Verma, S Srivastava","year":"2022","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Shah et al., 2022] N. Shah, P. Verma, T. Angle, and S. Srivastava. JEDAI: A system for skill-aligned explainable robot planning. In AAMAS, 2022.","title":"JEDAI: A system for skill-aligned explainable robot planning","authors":"N Shah, P Verma, T Angle, S Srivastava","year":"2022","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Srivastava, 2021] S. Srivastava. Unifying Principles and Metrics for Safe and Assistive AI. In AAAI, 2021.","title":"Unifying Principles and Metrics for Safe and Assistive AI","authors":"S Srivastava","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Verma and Srivastava, 2020] P. Verma and S. Srivastava. Learn- ing generalized models by interrogating black-box autonomous agents. In AAAI 2020 GenPlan Workshop, 2020.","title":"Learning generalized models by interrogating black-box autonomous agents","authors":"P Verma, S Srivastava","year":"2020","venue":"AAAI 2020 GenPlan Workshop","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Verma and Srivastava, 2021] P. Verma and S. Srivastava. Learn- ing causal models of autonomous agents using interventions. In IJCAI 2021 GenPlan Workshop, 2021.","title":"Learning causal models of autonomous agents using interventions","authors":"P Verma, S Srivastava","year":"2021","venue":"IJCAI 2021 GenPlan Workshop","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Verma et al., 2021] P. Verma, S. R. Marpally, and S. Srivastava. Asking the right questions: Learning interpretable action models through query answering. In AAAI, 2021.","title":"Asking the right questions: Learning interpretable action models through query answering","authors":"P Verma, S R Marpally, S Srivastava","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Verma et al., 2022] P. Verma, S. R. Marpally, and S. Srivastava. Discovering user-interpretable capabilities of black-box planning agents. In KR, 2022.","title":"Discovering user-interpretable capabilities of black-box planning agents","authors":"P Verma, S R Marpally, S Srivastava","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Verma et al., 2023] P. Verma, R. Karia, and S. Srivastava. Autonomous capability assessment of black-box sequential decision-making systems. In ICAPS 2023 KEPS Workshop, 2023.","title":"Autonomous capability assessment of black-box sequential decision-making systems","authors":"P Verma, R Karia, S Srivastava","year":"2023","venue":"ICAPS 2023 KEPS Workshop","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}