1
$\begingroup$

What is the relation between back-propagation and reinforcement learning?

$\endgroup$
6
$\begingroup$

Backpropagation is a subroutine often used when training Artificial Neural Networks with a Gradient Descent learning algorithm. Gradient Descent requires computation of the error gradient, i.e. derivatives, of a cost function with respect to the network parameters. BP allows you to find this gradient a lot faster than using naive methods. Reinforcement Learning refers to inferring "optimal" behavior, i.e. a strategy, of an agent maximizing some goal in an environment. Depending on the specific RL algorithm, BP may be employed to adjust parameters of a function approximator used to represent aspects of the environment and or the agent.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.