Value Function Approximation
Date and Time
This seminar touches on the Value Function Approximation methods. Linear and Non-linear methods (artificial neural networks) are discussed and how the stochastic gradient descent method is used to learn these approximations. Sample code is shown using a multi layer perceptron network to learn a value function together with an action policy.
권한이 없습니다. 로그인 부탁드립니다. You don't have permission to access. Please login.