Sublinear Regret for An Actor-Critic Algorithm in Continuous-Time Linear-Quadratic Reinforcement Learning.

Yilie Huang Yanwei Jia Xun Yu Zhou

Published in: CoRR (2024)

Keyphrases

actor critic
reinforcement learning
optimal control
dynamic programming
learning algorithm
computational complexity
k means
linear quadratic
optimal solution
linear programming
monte carlo
dynamical systems
approximate dynamic programming
expectation maximization
neuro fuzzy
control system
machine learning