Concept
Policy gradient
Policy gradient is a family of reinforcement learning methods that optimize a policy directly by following the gradient of expected reward with respect to the policy's parameters. Instead of learning a value function and acting greedily against it (as in Q-learning), you…
The rest of “Policy gradient” 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→