Tags » Reinforcement Learning

The math behind competitive Pokemon, Part 2: Value Function Approximation

The last post was about playing optimal Pokemon games by calculating the value function V(x) using Bellmann equations. Unfortunately, this was impractical, so we need another way to calculate the likelihood of winning games. 531 more words


The math behind competitive Pokemon, Part 1: Bellman Equations

One year ago I was drawn into the world of competitive Pokemon. It’s an incredible deep game that requires quite an effort to master. First you have to memorize a huge amount of information: Which type of attack is most effective against which type of Pokemon? 618 more words


Reinforcement Learning ile Optimal Yol Tespiti

Herkese Selam,

Bu yazıda Reinformcement Learning yöntemlerinden biri olan Q-Learning ile örnek bir harita üzerinden en optimum yolu bulan bir agent tasarımı yapacağım. Umarım farkındalık anlamında faydalı bir yazı olur. 1,505 more words

Teaching robots to learn how to learn

Robots will be part of our daily lives, Whether you like this idea or or not.

Most of the examples we have nowadays, remain limited to passively enaging machines who are focused on sharing information. 159 more words

IA (II): Paradigms

Today just a link to another post that was already in the blog to explain briefly:

  • Supervised learning.
  • Unsupervised learning.
  • Reinforcement learning.

Machine learning branches


Temporal Difference Learning in Python

So here I am after a quite long delay with another post. A lot happened during that time as I came back from our half-year South East Asia journey. 1,176 more words

Artificial Intelligence

Introduction to categories of Machine Learning

Supervised Learning

First let’s start with an example. How would you fix the price of a house you are selling? You will need to analyse a few things before fixing the price like number of rooms, area of the house, locality, age of the house, connectivity to shopping areas, etc. 453 more words

Deep Learning