Sunday, 31 Mar 2019 3:00 PM
RL Session 4:
1) Wrap up Markow Decision Process, Q-Learning
2) Introduce DQN (Deep Query Networks)
3) Explore Moutaincar-v0 models on OPENAI Gym
We want to grow an AI community in Rockville Science Space.
We welcome enthusiasts from all experience levels We encourage experts or more experienced members to join, and help in guiding our beginner AI & DL Enthusiasts.
What you need to bring is Curiosity..
Artificial Intelligence is a way of Life, it is here to stay, and everyday, it becomes more and more a part of our lives.
This series of talks will focus on the impacts of Deep Learning with respect to Reinforcement Learning. Our goal is to create practical projects with a little theory mixed in.
I will do an overview of key concepts of RL , a preview of AI related technical concepts.
I will set up a preface for Tensorflow and Keras.
In the latter sessions, we will be exploring Tensorflow paired with Keras, using Python and Jupyter Notebooks.
This is a multi-part talk, so don’t miss out on the foundation.
1) RL Basics
2) RL Basics & OPENAI Gym.
3) Introductory (Bellman Equation, Markov Decision Process, Q-Learning)
4) Deeper Dive in MDP, Q-Learning, DQN using OpenAI Gym
Standard Textbook: Reinforcement Learning by Richard S Sutton & Barto