Notes

Matrix Transformations – Linear Algebra

Linear Algebra, Mathematics
1. Functions and Transformations In standard algebra, a function takes a single number as an input and outputs a new number: f(x) = y. In Linear Algebra, we scale this concept up. A Transformation (often denoted as T) is a mathematical rule that takes an entire Vector as an input and assigns it to a ... Read More

Algebraic Properties of Matrices

Linear Algebra, Mathematics
1. Properties of Matrix Arithmetic Matrix arithmetic shares many rules with standard algebra, but there are crucial differences. Here are the core laws: Commutative Law for Addition: A + B = B + A Associative Law: A + (B + C) = (A + B) + C A(BC) = (AB)C Distributive Law: A(B + C) ... Read More

Bayesian Decision Theory

Machine Learning
Beginner’s Guide to Bayesian Decision Theory Making Sense of the Unknown The term “Bayesian Decision Theory” sounds like something you’d only hear in a graduate-level statistics lecture. It can definitely feel intimidating at first glance! But at its core, it’s actually a highly intuitive concept. In fact, it’s a mathematical formalization of how we naturally ... Read More

Calculus – $a^x$ and $log_a x$

Calculus, Mathematics
In calculus, exponential functions with a base other than e (like ax) and logarithms with base a (like loga x) are handled by converting them into their “natural” forms. Since the natural exponential ex and natural log ln(x) have very simple derivatives, we use them as the bridge to understand ax and loga x. Interactive ... Read More

Q-Learning Agent – Using DRL Toolbox

Deep Reinforcement Learning
Q Learning algorithm is: The figure below shows how a Q-learning agent trains on Q-Value function critic in order to estimate the optimal policy value. It follows epsilon greedy policy based on the value that is determined by the critic. The Internal Flow of a Q-Learning Agent Unlike basic algorithms, a Q-Learning agent splits its ... Read More

Types of RL Algorithms

Deep Reinforcement Learning
The Two Paths: Model-Free vs. Model-Based In Reinforcement Learning, the term “Model” is used to describe the rules of the environment. Specifically, a model consists of the Transition Dynamics (where an action takes you) and the Reward Function (what score that action earns). The biggest divide in algorithm design is whether the agent attempts to ... Read More

Key Concepts and Terminology in Reinforcement Learning

Deep Reinforcement Learning
The Agent-Environment Interaction In Reinforcement Learning, the two core components are the Agent and the Environment. The environment serves as the simulated or physical world where the agent operates. 🤖 Agent Action (a_t) Observation & Reward 🌍 Environment In a continuous loop, the agent receives an observation detailing the current condition of this world. Based ... Read More

Deep Reinforcement Learning

Deep Reinforcement Learning
What is Deep Reinforcement Learning? Demystifying Deep Reinforcement Learning How AI learns to make decisions through trial and error. Let’s break down deep reinforcement learning (DRL). It is a type of artificial intelligence where a computer program learns to make a sequence of decisions through trial and error, guided by a system of rewards. The ... Read More

Reinforcement Learning – Gymnasium

Deep Reinforcement Learning
If you want to teach an Artificial Intelligence to play a video game, control a robot, or optimize a trading strategy, you need an environment for it to practice in. Enter Gymnasium (formerly OpenAI Gym), the standard API for single-agent Reinforcement Learning (RL). 1. The Agent-Environment Loop Reinforcement learning is fundamentally about trial and error. We don’t ... Read More
error: