We study how to transfer representations pretrained on source tasks to t...
Despite the advancement of machine learning techniques in recent years,
...
Reinforcement learning constantly deals with hard integrals, for example...
Episodic training is a core ingredient of few-shot learning to train mod...
Constructing new and more challenging tasksets is a fruitful methodology...
Meta-learning researchers face two fundamental issues in their empirical...
Meta-learning methods, most notably Model-Agnostic Meta-Learning or MAML...
We study the variance of the REINFORCE policy gradient estimator in
envi...
Most stochastic optimization methods use gradients once before discardin...