Day: March 24, 2022

Policy Function and Value Function The goal of the optimal policy function is to maximize the expected discounted reward, even if this means taking actions that would lead to lower immediate next-step rewards from few states. Recall that from the previous lecture that for all s, the (optimal) value function is: where Estimating Transition Probabilities … Read more

What is the goal of reinforcement learning (RL), and how does it work? The goal of RL is to learn a good policy with none or limited supervision. RL Terminology Markov decision process (MDP) a set of states a set of actions Action dependent transition probabilities so thatReward functions , representing the reward for starting … Read more

A Gaussian Mixture Model (GMM), which is a generative model for data , is defined by the following set of parameters: K Number of mixture componentsA d-dimensional Gaussian for every : Mixture weightsThe parameters of a K-component GMM can be represented as:The likelihood of a point in a GMM is given as     Observed … Read more

Generative models model the probability distribution of each classDiscriminative models learn the decision boundary between the classes Simple Multinomial Generative model denotes the probability of model M choosing a word w. its value must lie between Likelihood Function For simplicity let’s consider W={0,1}. We want to estimate a multinomial model to generate a document D=”0101″. … Read more