CURL - Contrastive Unsupervised Representations for Reinforcement Learning
09 Apr 2020Introduction
-
The paper proposes a contrastive learning approach, called CURL, for performing...
The paper proposes a contrastive learning approach, called CURL, for performing...
The paper proposes a Competitive training mechanism to train a mixture...
The paper is among the first to study image classification at a large...
The paper proposes a simple and dataset-agnostic data augmentation mechanism called...
Masked Language Modeling (MLM) is a common technique for pre-training language-based...
Use of replay buffer (and rehearsal) is a common technique for...
The paper proposed a framework for joint modeling of labels and...
The paper proposes to build a universal neural machine translation system...
The paper studies observational overfitting: The phenomenon where an agent overfits...
The paper investigated two possible reasons behind the usefulness of MAML...