4 papers · 1 filter
Playing 2048 With Reinforcement Learning
Shilun Li, Veronica Peng
The game of 2048 is a highly addictive game. It is easy to learn the game, but hard to master as the created game revealed that only about 1% games out of hundreds million ever pla…
Distributionally Robust Classifiers in Sentiment Analysis
Shilun Li, Renee Li, Carina Zhang
In this paper, we propose sentiment classification models based on BERT integrated with DRO (Distributionally Robust Classifiers) to improve model performance on datasets with dist…
Ensemble ALBERT on SQuAD 2.0
Shilun Li, Renee Li, Veronica Peng
Machine question answering is an essential yet challenging task in natural language processing. Recently, Pre-trained Contextual Embeddings (PCE) models like Bidirectional Encoder…
Trajectory Prediction using Generative Adversarial Network in Multi-Class Scenarios
Shilun Li, Tracy Cai, Jiayi Li
Predicting traffic agents' trajectories is an important task for auto-piloting. Most previous work on trajectory prediction only considers a single class of road agents. We use a s…