Last week, we held the AI-ML Virtual forum of IsraelClouds and Ai-Blog, collaborating with IBM.
During the Forum, we heard two very interesting lectures. The first one was about Q-Learning for Beginners and the second was about practical and hands-on method of Reinforcement Q-Learning using Jupyter Notebook on the IBM Cloud
In the first session, Tamir Nave Algorithms Expert, spoke about the progress in the field of reinforcement learning that occurred thanks to the deep learning revolution. He Also explained the basic terms and concept and the famous algorithm q-learning.
In the second session, Tal Neeman, Developer Advocate, IBM, conducted a live Hands-on tutorial. Tal explained about the method of Reinforcement Q-Learning. to do so, he used IBM Watson Studio which is a simplify and scale data science platform, that enables to prepare data and build models, using open source codes or visual modeling.
To build the model, Tal will used Jupyter Notebook on the IBM Cloud and OpenAI Gym toolkit for developing and comparing reinforcement learning algorithms. It supports teaching agents everything, from walking to playing games like Pong or Pinball.
* As part of the Hands-on session, please note that you should Register IBM Cloud https://ibm.biz/BdqMxJ
You can further expand your knowledge and explore the topics above, by watching the 2 professional session here: https://www.israelclouds.com/article/israelclouds-ai-ml-virtual-forum-summary-2