Pic Credit : Samuel This is a colloboration event between GDG Mysore and TFUG Mysore Topic : Introduction to Reinforcement Learning using TF 2.0 - Samiran Roy Its Youtube Live event . Link will be available upon RSVP. Abstract: Reinforcement learning(RL) needs no introduction - we have seen robots teaching themselves how to play soccer, learning how to drive, learning how to dance by watching a youtube video, beating professional teams at Dota 2, and beating world champions at Go. RL was largely confined to academia for several decades and is now beginning to see some successful applications and products in the industry, in fields such as robotics, automated trading systems, manufacturing, energy, dialog systems and recommendation engines. For most companies, it is an exciting prospect due to the AI hype, however there is a lack of practical understanding/intuition on how/where to build RL models. This talk will attempt to bridge that gap by giving a practical introduction to RL, focusing on intuitively presenting the ideas from a software dev/problem solving perspective. It will also serve as a “starter pack” for people looking to get into the field. Bio: I am currently cofounding an early stage data driven startup called TildeHat. During my Masters at IIT Bombay, I spent my time developing deep learning, reinforcement learning, and computer vision software. I worked on a lot of cool AI - agents for self-driving cars, robot soccer, Atari games, and Carrom. As a part of my MTech thesis, I developed a Multi-Armed-Bandit framework for autonomous agents to supervise their own training.
Prior to this, I worked as a Senior Lead Data Scientist at Envestnet | Yodlee where I deployed Deep Learning, Reinforcement Learning, and Semi-Supervised learning-based products.
