Sample Efficient Paradigms for Personalized Assessment of Taskable AI Systems

Pulkit Verma

IJCAI 2023poster0 citations

Sample Efficient Paradigms for Personalized Assessment of Taskable AI Systems

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.

Planning and Scheduling: PS: Learning in planning and schedulingKnowledge Representation and Reasoning: KRR: Learning and reasoningKnowledge Representation and Reasoning: KRR: Reasoning about actionsPlanning and Scheduling: PS: Model-based reasoning

BibTeX

@inproceedings{ijcai2023p824,
  title     = {Sample Efficient Paradigms for Personalized Assessment of Taskable AI Systems},
  author    = {Verma, Pulkit},
  booktitle = {Proceedings of the Thirty-Second International Joint Conference on
               Artificial Intelligence, {IJCAI-23}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Edith Elkind},
  pages     = {7099--7100},
  year      = {2023},
  month     = {8},
  note      = {Doctoral Consortium},
  doi       = {10.24963/ijcai.2023/824},
  url       = {https://doi.org/10.24963/ijcai.2023/824},
}