activity
20152023
most citedEvaluating Large Language Models Trained on Code

1.5k citations · 3.5k across the 13 of their papers we have counts for

collaborators
Showing 2022Show all

2 papers · 1 filter

cs.LG2022

AutoDIME: Automatic Design of Interesting Multi-Agent Environments

Ingmar Kanitscheider, Harri Edwards

Designing a distribution of environments in which RL agents can learn interesting and useful skills is a challenging and poorly understood task, for multi-agent environments the di…

cs.LG2022★ 81 cited

Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Alethea Power, Yuri Burda, Harri Edwards +2

In this paper we propose to study generalization of neural networks on small algorithmically generated datasets. In this setting, questions about data efficiency, memorization, gen…