Notes

Fundmentals of Artificial Intelligence

What is artificial intelligence? Artificial Intelligence is the field of computer science that aims to teach machines to perform tasks similar to humans. We see AI systems in every day of our lives such as recommendation systems in websites, social media news feed etc. The core capabilities of AI system include perception, linguistic intelligence, reasoning, ... Read More

Deep Deterministic Policy Gradient (DDPG)

DDPG learns Q-function and a policy concurrently. Off-policy data and bellman equation are used to learn Q-function and then Q-function to lean policy. Q-function A Policy Learn concurrently Deep Deterministic Policy Gradient(DDPG) off-policydata + BellmanEquation learn Q-function Learn Policy DDGA is considered off-policy algorithm and is specially for continuous action spaces. Off-Policy Algorithm Continuous Action ... Read More

Multi-Agent Reinforcement Learning

Environment 👁️ Agent 1 {Action, Reward} 👁️ Agent 2 {Action, Reward} 👁️ Agent 3 {Action, Reward} (Autonomous Agents) (make their own decisions) Basics of MARL Multi-Agent Reinforcement Learning (MARL) extends traditional reinforcement learning by placing multiple autonomous agents into a shared environment. Instead of a single agent learning in isolation, agents in MARL must learn ... Read More

What is Statistical Modeling?

Statistics What can we learn from data? Mathematics + Statistics ➔ Statistical Model Statistical modeling is the process of applying mathematical formulations to describe the underlying probability distributions and relationships that generate a set of data. It provides a formal framework to represent both the predictable, systematic patterns in data and the inherent, random variability, ... Read More

Temporal Difference – Reinforcement Learning

Type of Incremental learning for prediction related problem [2]. Difference for conventional prediction learning: Conventional prediction – based on error between predicted and actual outcomes TD methods – based on error or difference between temporally successive predictions (if there is change in prediction over time, then learning occurs) Based on the paper [2] (page 10, ... Read More

Q-Learning

How does Q-Learning work? Learning in Q-Learning is similar to temporal differences (TD) [2] by Sutton. Steps involves (Found in paper [1] introduction section, second paragraph, Page 55). References:

Types of Reinforcement Learning

First, we need to understand the key nomenclature in reinforcement learning, which includes: Agent, Environment, Reward, Action, State, Policy Function, and Value Function. Terms Agent It takes action; e.g., if you are training a drone, then the drone is the agent. Environment Where the agent exists and moves. Actions What the agent performs on the ... Read More

Eigenvalues and Eigenvectors – Linear Algebra

What actually are eigenvalues and eigenvectors? For any square matrix $A$, an Eigenvector ($v$) and Eigenvalue ($\lambda$) satisfy the linear algebra equation. In other words, when $A$ is multiplied by the eigenvector ($v$), the resulting vector points in the exact same direction (or opposite), scaled only by the scaler factor $\lambda$. How to find eigenvalue? ... Read More
error: