Search Results for author:
Found 1 papers, 1 papers with code
ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e. g.,} BLEU and human feedback), but typically requires large-scale sampling over a space of action sequences.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
