[an error occurred while processing this directive] [an error occurred while processing this directive] [an error occurred while processing this directive] [an error occurred while processing this directive] Postdoctoral Researcher [an error occurred while processing this directive] Harvard University / Hebrew University, Israel [an error occurred while processing this directive] PhD '18 Technion - Israel Institute of Technology [an error occurred while processing this directive] [an error occurred while processing this directive] [an error occurred while processing this directive]

Artificial Intelligence

[an error occurred while processing this directive] Automated Design of Better Environments for Intelligent Agents [an error occurred while processing this directive] The last decade has seen great advances in AI research and the deployment of AI methods across a range of systems. Even so, AI’s full potential has yet to be realized with major challenges remaining for many tasks autonomous AI agents could potentially perform and assist people with. Most past research aimed at increasing the capabilities of AI methods has focused exclusively on the AI agent itself, i.e., given some input, what are the improvements to the agent’s reasoning that will yield the best possible output. In my research, I take a novel approach to increasing the capabilities of AI agents via the design of the environments in which they are intended to act. My methods for automated design identify the inherent capabilities and limitations of AI agents with respect to their environment and find the best way to modify the environment to account for those limitations and maximize the agents’ performance.

My presentation will describe some of my research projects that vary in their design objective, in the AI methodologies that are applied for finding optimal designs, and in the real-world applications to which the settings correspond. One example is Goal Recognition Design (GRD), which seeks a redesign to an environment that minimizes the maximal progress an agent can make before its goal is revealed. A second is Equi-Reward Utility Maximizing Design (ER-UMD), which seeks to maximize the performance of a planning agent in a stochastic environment. The third, Reinforcement Learning Design (RLD), parallels ER-UMD, but considers an environment with reinforcement learning agents. I will also discuss how the different frameworks fit within my overreaching objective of using automated design to promote effective multi-agent collaboration and to enhance the way robots and machines interact with humans. [an error occurred while processing this directive] Sarah Keren is a postdoctoral fellow at Harvard University, where she is affiliated with the Center for Research on Computation and Society (CRCS), and Hebrew University. She completed her Ph.D. at the Technion - Israel Institute of Technology. Sarah's research in the field of artificial intelligence (AI) focuses on increasing the capabilities of AI agents via the design of the environments in which they are intended to act. Her methods for automated design identify the inherent capabilities and limitations of AI agents with respect to their environment and find the best way to modify the environment to account for those limitations and maximize the agents’ performance. Her long-term goal is to provide the theoretical foundations for designing AI systems that are capable of effective partnership in sustainable and efficient collaborations of automated agents as well as of automated agents and people.

Sarah’s work has appeared in leading AI conferences (AAAI, ICAPS, KR, IROS and IJCAI) and the Journal of Artificial Intelligence Research (JAIR). She has received different excellence awards including Best Paper Honorable Mention at ICAPS 2014, Best Dissertation Award Honorable Mention at ICAPS 2020, the Eric and Wendy Schmidt Postdoctoral Award for Women in Mathematical and Computing Sciences, and the Weizmann Institute of Science National Postdoctoral Award for Advancing Women in Science. [an error occurred while processing this directive] Personal home page [an error occurred while processing this directive] [an error occurred while processing this directive]