@online{huang2025rl,
  author       = {Huang, Xuanqiang Angelo},
  title        = {{RL} Function Approximation},
  date         = {2025-01-17},
  organization = {Xuanqiang Angelo Huang's Blog},
  url          = {https://flecart.github.io/notes/rl-function-approximation/},
  langid       = {english},
  abstract     = {These algorithms are good for scaling state spaces, but not actions spaces. The Gradient Idea \# Recall Temporal difference learning and Q-Learning, two model free policy evaluation techniques explored in Tabular Reinforcement Learning . A simple parametrization \# The idea here is}
}