About the Talk:
One of the challenges in constructing a two level system, for instance, a higher-level deliberative planner with a lower level reactive RL agent, is the interface between these two systems. In this talk, I argue that this interface is crucial in constructing appropriate abstractions for the underlying RL agent to be efficient and effective. Specifically, I outline our RePReL system that constructs these abstractions automatically using a dynamic Statistical Relational Learning (SRL) language. Our experiments show that RePReL framework not only achieves better performance and efficient learning on the task at hand but also demonstrates better generalization to unseen tasks. The interface layer allows for the RL and planner components to be a plug and play system and I demonstrate the versatility of our approach on several tasks. This is joint work with our PhD student Harsha Kokel, Prasad Tadepalli and Balaraman Ravindran.
About the Speaker
Prof. Sriraam Natarajan is a Professor at the Department of Computer Science at University of Texas Dallas, a Hessian.ai fellow at TU Darmstadt and a RBDSCAI Distinguished Faculty Fellow at IIT Madras. His research interests lie in the field of Artificial Intelligence, with emphasis on Machine Learning, Statistical Relational Learning and AI, Reinforcement Learning, Graphical Models and Biomedical Applications. He is a AAAI senior member and has received the Young Investigator award from US Army Research Office, Amazon Faculty Research Award, Intel Faculty Award, XEROX Faculty Award, Verisk Faculty Award and the IU trustees Teaching Award from Indiana University. He is the AAAI program co-chair of AAAI 2024, AI and society track chair of AAAI 2022 and 2023, demo chair of IJCAI 2022, program co-chair of SDM 2020 and ACM CoDS-COMAD 2020 conferences. He was the speciality chief editor of Frontiers in ML and AI journal, and is an associate editor of MLJ, JAIR, DAMI and Big Data journals.
Click on this Zoom-Link to join us online.