Policy Gradients are a reinforcement learning algorithm that learns the optimal policy for a given task by updating the policy parameters in the direction of the gradient of the expected reward. This unit will introduce the concepts and techniques of Policy Gradients and their applications in various domains. Üben mit sofortiger Rückmeldung, kostenlos und ohne Anmeldung.

Weitere Themen

• Linear Regression
• Logistic Regression
• Decision Trees
• Clustering
• Dimensionality Reduction
• Q-Learning