Reinforcement Learning allows machines and software agents to automatically determine the best course of behavior within a set context – with applications ranging from allowing computers to solve games, to autopilot systems and robot tasks training, this area of learning has never been more relevant. However, Reinforcement Learning isn’t perfect, and often has issues in dealing with more complex tasks. This is where Deep Reinforcement Learning comes in!
Through this course you will be given the theoretical understanding of Deep Reinforcement Learning as you build your own Deep Reinforcement Agents and teach them how to play complex, Atari-style games.
What you will learn:
- The theoretical concepts underlying Reinforcement Learning
- How to define games so that you can build algorithms to help solve them
- Addressing the problems inherent in Reinforcement Learning with Value Iterations
- Using Q-Learning to improve upon Value Iteration
- Using Deep Q-Networks to solve complex games