Research aims to make language models safer and more useful for users.
― 6 min read
Bernardo Avila Pires
A new method enhances decision-making in reinforcement learning through action-conditional predictions.
― 7 min read
Cutting edge science explained simply
Research aims to make language models safer and more useful for users.
― 6 min read
A new method enhances decision-making in reinforcement learning through action-conditional predictions.
― 7 min read