Concept
Critic
In reinforcement learning, the critic is a learned function that estimates how good a state or action is, so the policy (the actor) gets a lower-variance signal to update from. It is the "critic" half of actor-critic methods: the actor picks actions, the critic…
The rest of “Critic” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→