Ai+ Training

In recent years, there has been increased interest in the field of deep reinforcement learning (DRL), fuelled mainly by its performance in Atari Games and the win of AlphaGo over Mr. Lee Sedol, a Dan 9 Go player. Unlike supervised learning, reinforcement learning does not require labeled data. Here the agent learns through its interaction with the environment. DRL combines deep learning for sensory processing along with reinforcement learning algorithms. In this interactive training, you will be introduced to some of the most popular and successful DRL algorithms. We will start with an introduction to different learning paradigms and how DRL differs from them. We will introduce the OpenAI reinforcement learning environment and learn how to use the OPenAI Gym to design your (custom) environments. The two major RL methods: value-based methods and policy-based methods will be explored. We will cover the Deep Q Network and use it to solve a discrete action space environment. Policy gradient methods will also be explored with a special emphasis on continuous action space and multi-agent environment. Finally, we will cover the pros and cons of different algorithms and proposed variations in them. The training session will include a hands-on session where you will build an RL agent for playing Atari. Additionally, we will cover how to use RL agents in other applications like robotics, the financial sector, etc.