We show how an action-dependent baseline can be used by the policy gradient theorem using function approximation, originally presented with action-independent baselines by (Sutton et al. 2000).
Cite
@article{arxiv.1706.06643,
title = {Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines},
author = {Philip S. Thomas and Emma Brunskill},
journal= {arXiv preprint arXiv:1706.06643},
year = {2017}
}