← Search

Tim Scholtes

2 accepted papers

2022

CoBERL: Contrastive BERT for Reinforcement Learning

ICLR 2022spotlight

Many reinforcement learning (RL) agents require a large amount of experience to solve tasks. We propose Contrastive BERT for RL (COBERL), an agent that combines a new contrastive loss and a hybrid LSTM-transformer architecture to tackle the challenge of improving data efficiency. COBERL enables effi…

2022

StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models

ICML 2022spotlight

Knowledge and language understanding of models evaluated through question answering (QA) has been usually studied on static snapshots of knowledge, like Wikipedia. However, our world is dynamic, evolves over time, and our models’ knowledge becomes outdated. To study how semi-parametric QA models and…