← Jargon

Jargonmachine learning· 30 claims· 10 episodes

value function

In reinforcement learning, a function estimating the expected future reward of a state or action, allowing credit assignment before a final outcome.

As defined in Ilya Sutskever – We're moving from the age of scaling to the age of research


Where it comes up · 10

and 2 more


Most important claims · 10 of 30Search all claims for “value function” →