Bauer, Stefan

The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents

2021 · arXiv (Cornell University)

Building sample-efficient agents that generalize out-of-distribution (OOD) in real-world settings remains a fundamental unsolved problem on the path towards achieving higher-level cognition. One particularly promising approach is to begin with low-dimensional, pretrained representations of our …

Understanding Causality with Large Language Models: Feasibility and Opportunities

2023 · arXiv (Cornell University)

We assess the ability of large language models (LLMs) to answer causal questions by analyzing their strengths and weaknesses against three types of causal question. We believe that current LLMs can answer causal questions with …