GROOT: Corrective Reward Optimization for Generative Sequential Labeling.
Kazuma HashimotoKarthik RamanPublished in: CoRR (2022)
Keyphrases
- unsupervised learning
- optimization algorithm
- optimization methods
- global optimization
- reinforcement learning
- real time
- generative model
- image segmentation
- information retrieval
- training data
- multi agent
- optimization process
- active learning
- neural network
- optimization method
- data sets
- optimization model
- database
- discrete optimization
- pairwise
- support vector
- machine learning