Timezone: »
Revisiting Value Alignment Through the Lens of Human-Aware AI
Sarath Sreedharan · Subbarao Kambhampati
Event URL: https://openreview.net/forum?id=oKJqyvp_eQY »
Value alignment has been widely argued to be one of the central safety problems in AI. While the problem itself arises from the way humans interact with the AI systems, most current solutions to value alignment tend to sideline the human or make unrealistic assumptions about possible human interactions. In this position paper, we propose a human-centered formalization of the value alignment problem that generalizes human-AI interaction frameworks that were originally developed for explainable AI. We see how such a human-aware formulation of the problem provides us with novel ways of addressing and understanding the problem.
Author Information
Sarath Sreedharan (CSU)
Subbarao Kambhampati (Arizona State University)
More from the Same Authors
-
2021 Spotlight: Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation »
Lin Guan · Mudit Verma · Sihang Guo · Ruohan Zhang · Subbarao Kambhampati -
2022 : Large Language Models Still Can't Plan (A Benchmark for LLMs on Planning and Reasoning about Change) »
Karthik Valmeekam · Alberto Olmo · Sarath Sreedharan · Subbarao Kambhampati -
2022 : Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion »
Utkarsh Soni · Sarath Sreedharan · Mudit Verma · Lin Guan · Matthew Marquez · Subbarao Kambhampati -
2022 : Advice Conformance Verification by Reinforcement Learning agents for Human-in-the-Loop »
Mudit Verma · Ayush Kharkwal · Subbarao Kambhampati -
2022 : Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences »
Lin Guan · Karthik Valmeekam · Subbarao Kambhampati -
2021 Poster: Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation »
Lin Guan · Mudit Verma · Sihang Guo · Ruohan Zhang · Subbarao Kambhampati -
2020 : Panel #2 »
Oren Etzioni · Heng Ji · Subbarao Kambhampati · Victoria Lin · Jiajun Wu -
2013 Poster: Synthesizing Robust Plans under Incomplete Domain Models »
Tuan A Nguyen · Subbarao Kambhampati · Minh Do -
2012 Poster: Action-Model Based Multi-agent Plan Recognition »
Hankz Hankui Zhuo · Qiang Yang · Subbarao Kambhampati