← Search

Abraham J Fetterman

2 accepted papers

2023

On the Stepwise Nature of Self-Supervised Learning

ICML 2023poster

We present a simple picture of the training process of self-supervised learning methods with dual deep networks. In our picture, these methods learn their high-dimensional embeddings one dimension at a time in a sequence of discrete, well-separated steps. We arrive at this picture via the study of a…

2022

Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds

NeurIPS 2022accept

Despite impressive successes, deep reinforcement learning (RL) systems still fall short of human performance on generalization to new tasks and environments that differ from their training. As a benchmark tailored for studying RL generalization, we introduce Avalon, a set of tasks in which embodied…

Cited by 25SourcePDFScholar