On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR.
Jaeuk ShinGiho KimHowon LeeJoonho HanInsoon YangPublished in: CoRR (2023)
Keyphrases
- loss function
- reinforcement learning
- pairwise
- squared error
- logistic regression
- optimal control
- support vector
- risk minimization
- learning to rank
- reproducing kernel hilbert space
- convex loss functions
- loss minimization
- function approximation
- hinge loss
- empirical risk
- dynamic programming
- active learning
- information retrieval
- bregman divergences