Intro to Reinforcement Learning (study group)

Our next MLT study session is coming up on August 3 at the Tokyo Metropolitan Library. "Intro to RL" is the kick-off for a series of Reinforcement Learning study sessions.

The MLT RL sessions aim at building a solid understanding of RL core concepts to state-of-art algorithms. We will look at how RL problems are formulated and how to build Deep Reinforced Learning models.

-- AGENDA --
14:00-15:00: Welcome note and presentation by Anugraha Sinha, Senior Data Scientist at NEC Corporation
15:00-16:00: Implementation
16:00-17:00: Code exercise, open working session, wrap up

Presentation

1. Introduction to RL
2. Important elements of an RL problem
3. Description of Markov Decision Process (MDP) and and Markov Assumption.
4. Importance of parametrization of State, Action, Reward and Environment.
5. Model Based and Model Free Methods
6. Meaning of Control Problem and Evaluation Problem.
7. Algorithm of Policy Evaluation and Value iteration methods

Code examples

1. Finding the best route through a maze/obstruction avoidance using policy iteration algorithm.
2. Above problem statement with value iterations algorithm.
3. Code exercise

-- PREREQUISITE --

• 1 year of coding experience
• Make sure to cover the basics of Python programming

-- JOIN US --
ML engineers, researchers and students can join MLT on:
[Slack] https://goo.gl/WnbYUP

-- MLT PATRON --
Become a MLT Patron and help us to keep MLT meetups like this inclusive and for free. https://www.patreon.com/MLTOKYO

Find MLT resources
Github: https://github.com/Machine-Learning-Tokyo
Youtube: https://www.youtube.com/MLTOKYO

-- RECRUITING --
MLT events are for community building and knowledge sharing. We politely ask that company representatives, recruiters and consultants looking to hire or sell their services do not come to this event.