Finite Time Analysis of Temporal Difference Learning with Linear Function by L. A. Prashanth

Explore a 49-minute lecture on "Finite Time analysis of Temporal Difference Learning with Linear Function Approximation" presented by L. A. Prashanth at the International Centre for Theoretical Sciences. Part of a discussion meeting on Data Science: Probabilistic and Optimization Methods, this talk delves into advanced topics in machine learning and reinforcement learning. Gain insights into temporal difference learning algorithms, their convergence properties, and applications in data-driven decision-making processes. Suitable for researchers, data scientists, and advanced students interested in the theoretical foundations of reinforcement learning and its intersection with data science and optimization methods.