Bias and Variance tradeoff in Policy Gradient — Policy gradient methods are one of the most widely used learning algorithms in reinforcement learning. They aim to optimize a parameterized policy and use value functions to help estimate how the policy should be improved. One of the major issues in reinforcement learning though, especially for policy gradient methods, is…

Algorithms behind ChatGPT and Google Bard — In the early days, NLP systems are mostly rule-based that are later replaced by machine learning models. Training deep learning language models from scratch requires a large amount of labeled data which is expensive to generate while it is very easy to get large volumes of unlabeled text data. In…

A*, Dijkstra, Dynamic Programming, BFS, DFS and IDDFS — In Machine Learning, search problems are a type of state-based models with many applications. For example, route finding, robot motion planning and machine translation. In this article, we will delve into several common search algorithms and see how they are used to solve different tasks. The rest of the article…

Vanilla Policy Gradient Algorithm and Implementation in Tensorflow — Policy gradient methods are very popular reinforcement learning(RL) algorithms. They are very useful in that they can directly model the policy, and they work in both discrete and continuous space. In this article, we will: have a short overview of the underlying math of policy gradient; implement the policy gradient…

Unsupervised and Semi-supervised Gaussian Mixture Models (GMM) — When companies launch a new product, they usually want to find out the target customers. If they have data on customers’ purchasing history and shopping preferences, they can utilize it to predict what types of customers are more likely to purchase the new product. …

Actor Critic, Policy Gradient, DQN, VFA, SARSA, Q-learning, Model-based and Model-free Monte Carlo, Dynamic Programming — Reinforcement learning has gained tremendous popularity in the last decade with a series of successful real-world applications in robotics, games and many other fields. In this article, I will provide a high-level structural overview of classic reinforcement learning algorithms. …

A Comparison of Naive Bayes and Logistic Regression — Generative and discriminative models are widely used machine learning models. For example, Logistic Regression, Support Vector Machine and Conditional Random Fields are popular discriminative models; Naive Bayes, Bayesian Networks and Hidden Markov models are commonly used generative models. Probabilistic graphical models (PGMs) are a rich framework for encoding probability distributions…

Concepts and Code Implementation — In this tutorial, I will show you how to implement the Gibbs Sampling algorithm to denoise images. Our goal is to restore the true image(left) by removing noise from a corrupted image(right) using Gibbs Sampling — a Markov Chain Monte Carlo (MCMC) method.

In this tutorial, I will introduce to you how to train a Deep Q-net(DQN) model to play the CartPole game. We will use OpenAI’s Gym and TensorFlow 2. This article assumes some familiarity with Reinforcement Learning and Deep Learning. What is Reinforcement Learning and DQN? Let’s start with a quick refresher of Reinforcement Learning and the…