Francesco Locatello

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 …

Scalable Causal Discovery with Score Matching

2023 · arXiv (Cornell University)

This paper demonstrates how to discover the whole causal graph from the second derivative of the log-likelihood in observational non-linear additive Gaussian noise models. Leveraging scalable machine learning approaches to approximate the score function $\nabla …