Taming Wild Reward Functions: The Score Function Gradient Estimator Trick
This post explains the need for the score function gradient estimator trick and how it works.
Posts by Category
explanation
paper discussion
RL in NMT: The Good, the Bad and the Ugly
Discussing good, bad and ugly practices of reinforcement learning in neural machine translation.
opinion piece
RL in NMT: The Good, the Bad and the Ugly
Discussing good, bad and ugly practices of reinforcement learning in neural machine translation.
overview
Counterfactual Learning of Semantic Parsers When Even Gold Answers Are Unattainable
How can we train semantic parsers if neither question-parse nor question-answer pairs can be collected?