Eigensubspace of Temporal-Difference Dynamics and How It Improves Value Approximation in Reinforcement Learning

Qiang He, Tianyi Zhou 0001, Meng Fang, Setareh Maghsudi. Eigensubspace of Temporal-Difference Dynamics and How It Improves Value Approximation in Reinforcement Learning. In Danai Koutra, Claudia Plant, Manuel Gomez-Rodriguez, Elena Baralis, Francesco Bonchi, editors, Machine Learning and Knowledge Discovery in Databases: Research Track - European Conference, ECML PKDD 2023, Turin, Italy, September 18-22, 2023, Proceedings, Part IV. Volume 14172 of Lecture Notes in Computer Science, pages 573-589, Springer, 2023. [doi]

Abstract

Abstract is missing.