NanReinforcement learning: Q-learner with detailed example and code implementationIn a previous story, we introduced the concept of Q-learning. Today, we will implement that concept and build a Q-leaner in Python. Let’s…9 min read·Jun 23, 2022----
NanReinforcement learning: concepts of Q-learningToday we focus on developing the concept of Q-learning to solve a MDP. We will talk about the pseudo-code and Python implementation of…12 min read·Jun 6, 2022----
NanReinforcement learning: Model-free MC learner with code implementationToday we focus on building a Monte Carlo (MC) agent to learn a MDP. In a previous story, we implemented a model-based ADP learner which…14 min read·May 31, 2022--1--1
NanReinforcement learning: model-based ADP learner with code implementationIn today’s story we focus on building a model-based adaptive dynamic programming (ADP) agent to learn an MDP. As we explained in great…14 min read·Jan 29, 2022--1--1
NanMarkov decision process: value iteration with code implementationIn today’s story we focus on value iteration of MDP using the grid world example from the book Artificial Intelligence A Modern Approach by…9 min read·Dec 20, 2021--4--4
NanMarkov decision process: policy iteration with code implementationIn today’s story we focus on policy iteration of MDP. We are still using the grid world example from the book Artificial Intelligence A…16 min read·Dec 19, 2021--5--5
NanMarkov decision process: basicsMarkov decision process (MDP) is an important concept in AI and is also part of the theoretical foundation of reinforcement learning. In…13 min read·Dec 4, 2021--5--5
NanComplete guide of Linear Regression built from scratchLinear regression is a supervised learning algorithm that has a deep root from statistics. It is one of the machine learning algorithms…25 min read·Nov 22, 2021----