Nature, Published online: 07 June 2023; doi:10.1038/d41586-023-01812-5
Deep reinforcement learning has been used to improve computer code by treating the task as a game — with no special knowledge needed on the part of the player. The result has already worked its way into countless programs.
More News
I study artefacts left in prehistoric caves
How artificial intelligence is helping to identify global inequalities
Tackling ‘wicked’ problems calls for engineers with social responsibility