Deep Reinforcement Learning: Policy Gradient and Value Function

Related lectures (29)

Introduces policy gradient methods using a simple example of a single neuron with binary output.

Introduces Q-Learning, Deep Q-Learning, REINFORCE algorithm, and Monte-Carlo Tree Search in reinforcement learning, culminating in AlphaGo Zero.

Delves into deep learning optimization, challenges, SGD variants, critical points, overparametrized networks, and adaptive methods.

Covers the fundamentals of deep learning, from artificial neurons to modern networks.

Explores the Random Feature Method for solving PDEs using machine learning algorithms to approximate high-dimensional functions efficiently.

Introduces Convolutional Neural Networks, explaining their architecture, training process, and applications in semantic segmentation tasks.

Covers the back-propagation algorithm for deep neural networks and the importance of locality in CNN.

Explores the statistical mechanics of learning, focusing on neural networks' mysteries and computational challenges.

Explores reinforcement learning in AI to master games using neural networks.

Page 2 of 2