Embedded Files
Talk Date and Time: September 5, 2023 at 6:30 pm - 7:15 pm EST followed by 15 minutes of Q&A on Google Meet
Topic: RLing in the Deep
Abstract:
Deep reinforcement learning has been applied successfully to a number of challenging tasks. Despite this, we have very little understanding of its learning dynamics; I'd argue that some of our assumptions of how deep RL networks evolve have been incorrectly carried over from insights in the supervised learning literature. Over the past few years I have focused a lot of my research on developing a better empirical understanding of the learning dynamics of deep RL networks, which have often led to improved algorithms. In this talk I will present some of these findings and discuss some avenues for future work.
Bio:
Pablo Samuel was born and raised in Quito, Ecuador, and moved to Montreal after high school to study at McGill. He obtained his PhD from McGill, focusing on Reinforcement Learning under the supervision of Doina Precup and Prakash Panangaden. He has been working at Google for over 11 years, and is currently a staff research Software Developer in Google DeepMind in Montreal, focusing on fundamental Reinforcement Learning research, Machine Learning and Creativity, and being a regular advocate for increasing the LatinX representation in the research community. Aside from his interest in coding/AI/math, Pablo Samuel is an active musician.
Page updated
Google Sites
Report abuse