1.5k citations · 3.5k across the 13 of their papers we have counts for
13 papers
Let's Verify Step by Step
Hunter Lightman, Vineet Kosaraju, Yura Burda +7
In recent years, large language models have greatly improved in their ability to perform complex multi-step reasoning. However, even state-of-the-art models still regularly produce…
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…
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…
Unsupervised Neural Machine Translation with Generative Language Models Only
Jesse Michael Han, Igor Babuschkin, Harrison Edwards +8
We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models. Our method consists of three steps: few-shot a…
Evaluating Large Language Models Trained on Code
Mark Chen, Jerry Tworek, Heewoo Jun +55
We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities. A distinct production version of Codex p…
Exploration by Random Network Distillation
Yuri Burda, Harrison Edwards, Amos Storkey +1
We introduce an exploration bonus for deep reinforcement learning methods that is easy to implement and adds minimal overhead to the computation performed. The bonus is the error o…