We explore the novel application of Large Language Models to code
optimi...
We release Code Llama, a family of large language models for code based ...
Demonstrations provide insight into relevant state or action space regio...
In reinforcement learning, pre-trained low-level skills have the potenti...
We formulate the problem of defogging as state estimation and future sta...
We consider the problem of high-level strategy selection in the adversar...
We release a dataset of 65646 StarCraft replays that contains 1535 milli...
The prevalent approach to sequence to sequence learning maps an input
se...
The prevalent approach to neural machine translation relies on bi-direct...