Sarath Sreedharan
Date:
Speaker
Sarath Sreedharan is an Assistant Professor at Colorado State University. His core research interests include designing human-aware decision-making systems that can generate behaviors that align with human expectations. He completed his PhD from Arizona State University, where his doctoral dissertation received one of the 2022 Dean’s Dissertation Award for Ira A. Fulton Schools of Engineering. His research has been published in various premier research conferences, including AAAI, ICAPS, IJCAI, AAMAS, IROS, HRI, ICRA, ICML and ICLR, and journals like AIJ, and has, to date, garnered over 1500 citations. He has presented tutorials on his research at various forums and is the lead author of a Morgan Claypool monograph on explainable human-AI interactions. He was selected as a DARPA Riser Scholar for 2022 and a Highlighted New Faculty by AAAI. His research has won multiple awards, including the Best System’s Demo and Exhibit Award at ICAPS-20 and Best Paper Award at Bridging Planning & RL workshop at ICAPS 2022. He was also recognized as a AAAI-20 Outstanding Program Committee Member, Highlighted Reviewer at ICLR 22, IJCAI 2022 Distinguished Program Committee Member and Top Reviewer at NeurIPS 22.
Speaker Links: Personal Website - Google Scholar
Abstract
We are living through a revolutionary moment in AI history. We are seeing the development of impressive new AI systems at a rate that was unimaginable just a few years ago. However, AI’s true potential to transform society remains unrealized, in no small part due to the inability of current systems to work effectively with people. A major hurdle to achieving such coordination is the inherent asymmetry between the AI system and its users. In this talk, I will discuss how the framework of Human-Aware AI (HAAI) provides us with the tools required to bridge this gap and support fluent and intuitive coordination between the AI system and its users.
Papers:
- Sreedharan, Sarath, Tathagata Chakraborti, and Subbarao Kambhampati. Foundations of explanations as model reconciliation. Artificial Intelligence 301 (2021): 103558.
- Sreedharan, Sarath, Siddharth Srivastava, and Subbarao Kambhampati. Using state abstractions to compute personalized contrastive explanations for AI agent behavior. Artificial Intelligence 301 (2021): 103570.
- Sreedharan, Sarath, et al. Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations. International Conference on Learning Representations.