what is the difference between "actor-critic training" and "REINFORCE-critic" in the README.md ?
haoyusoong opened this issue · comments
I may have figured it out. "2 .actor-critic training" is the step3 of algorithm 2 in the paper .
The source code for "An Actor Critic Algorithm for Structured Prediction"
haoyusoong opened this issue · comments
I may have figured it out. "2 .actor-critic training" is the step3 of algorithm 2 in the paper .