Linear Function Approximation
Linear function approximation aims to efficiently represent value functions in reinforcement learning and other sequential decision-making problems by using linear combinations of features. Current research emphasizes developing provably efficient algorithms for various settings, including those with off-policy learning, delayed feedback, heavy-tailed rewards, and multiple agents, often employing techniques like temporal difference learning, fitted Q-iteration, and natural policy gradients. These advancements address the computational challenges of large state spaces and improve the theoretical understanding and practical performance of reinforcement learning algorithms, impacting fields like robotics, control systems, and AI safety.
Papers
February 11, 2024
February 6, 2024
January 26, 2024
December 22, 2023
December 16, 2023
October 29, 2023
October 22, 2023
September 28, 2023
July 5, 2023
June 12, 2023
June 7, 2023
May 30, 2023
May 25, 2023
May 10, 2023
March 9, 2023
March 1, 2023
February 27, 2023
February 26, 2023
February 25, 2023
February 7, 2023