Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model.

Haikang Deng Colin Raffel

Published in: CoRR (2023)

Keyphrases

reinforcement learning
probabilistic model
probability distribution
mathematical model
statistical model
high level
formal model
neural network
machine learning
objective function
management system
theoretical analysis
computational model
theoretical framework
experimental data
bi directional