Non-linear function approximation

Critic-Actor for Average Reward MDPs with Function Approximation: A Finite-Time Analysis

root February 5, 2024 0

This research presents the first critic-actor algorithm with function approximation and finite-time analysis, used in the long-run average reward setting. The algorithm is designed to solve reinforcement learning problems by…

Machine Learning

Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning

root October 3, 2023 0

The paper proposes an algorithm, Pessimistic Nonlinear Least-Square Value Iteration (PNLSVI), for offline reinforcement learning with non-linear function approximation. The algorithm includes three innovative components: a variance-based weighted regression scheme,…

Page 1 of 1

Press ESC to close

Non-linear function approximation

Please allow ads on our site