AI Seminar Series 2024: Offline RL Needs Less Data if you Have Trajectories, Vlad Tkachuk
The AI Seminar is a weekly meeting at the University of Alberta where researchers interested in artificial intelligence (AI) can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics can be related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems.
Abstract:
We study offline reinforcement learning with linear value function approximation. Previous work showed that learning a nearly optimal policy is impossible without a large dataset size, even with a data coverage assumption. This work left open whether trajectory data could overcome this issue. We show that with trajectory data, a dataset of size polynomial in feature dimension, horizon, and data coverage coefficient suffices for learning a nearly optimal policy. The question of computational efficiency remains open.
Presenter Bio:
Vlad Tkachuk is a first-year PhD student in Computing Science at the University of Alberta, working under the supervision of Csaba Szepesvári and Xiaoqi Tan. He completed his master's degree at the University of Alberta, also under the supervision of Csaba Szepesvári. Before that, he obtained his bachelor's in Electrical Engineering from the University of Waterloo. His research interests lie primarily in reinforcement learning theory.
Watch video AI Seminar Series 2024: Offline RL Needs Less Data if you Have Trajectories, Vlad Tkachuk online without registration, duration hours minute second in high quality. This video was added by user Amii 26 August 2024, don't forget to share it with your friends and acquaintances, it has been viewed on our site 261 once and liked it 3 people.