2021-10-01

REINFORCE Algorithm explained in Policy-Gradient based methods

Policy gradients Policy gradients is a family of algorithms for solving reinforcement learning problems by directly optimizing the policy in […]
2021-09-24

Deep Reinforcement Learning: Using policy-based methods to play Pong from pixels

This is a long-overdue blog post on Reinforcement Learning (RL). RL is hot! You may have noticed that computers can […]
2021-09-17

Evolution Strategies as a Scalable Alternative to Reinforcement Learning

Evolution strategies (ES) is an optimization technique that’s been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on […]
2021-09-10

Double DQN and Dueling DQN in Reinforcement Learning

In this part, we will see two algorithms that improve upon DQN. These are named Double DQN and Dueling DQN. But first, let’s […]
2021-09-09

SumTree data structure for Prioritized Experience Replay (PER) explained with Python Code

Weighted sampling from a list-like collection is an important activity in many applications. Weighted sampling involves selecting samples randomly from […]
2021-04-20

Improvements in Deep Q Learning: Dueling Double DQN, Prioritized Experience Replay, and fixed Q-targets

Deep Q-Learning was introduced in 2014. Since then, a lot of improvements have been made. So, today we’ll see four […]
2019-12-07

Difference between model-based and model-free reinforcement learning

To answer this question, lets revisit the components of an MDP, the most typical decision making framework for RL. An […]
2019-12-06

What is q-learning?

Introduction One of my favorite algorithms that I learned while taking a reinforcement learning course was q-learning. Probably because it […]