On task-relevant loss functions in meta-reinforcement learning.
Jaeuk ShinGiho KimHowon LeeJoonho HanInsoon YangPublished in: L4DC (2024)
Keyphrases
- loss function
- reinforcement learning
- pairwise
- loss minimization
- learning to rank
- support vector
- squared error
- logistic regression
- empirical risk
- reproducing kernel hilbert space
- convex loss functions
- function approximation
- risk minimization
- boosting algorithms
- hinge loss
- temporal difference learning
- machine learning
- text categorization
- square loss
- learning algorithm