Reinforcement learning is a powerful machine learning technique, in which it lead to a functional AGI system is debatable. RL is a artificial intelligence technology that can be used to learn strategies to optimally control large, complex systems such as manufacturing plants, traffic control systems (road/train/aircraft), financial portfolios, robots, etc. Right now, it transitioning from research labs to highly impactful, real world applications. For example, self-driving car companies are like Wayve and Waymo using reinforcement learning to develop the control systems for their cars.

Artificial Intelligence systems that are typically used in industry perform pattern recognition to make a prediction. For an instance, they might to recognize the patterns in images to detect faces (face detection), or recognize patterns in sales data to predict a change in demand (demand forecasting), and so on. On the other hand, Reinforcement learning methods, are used to make optimal decisions or take optimal actions in applications where there is a feedback loop.

Many of the recent, prominent demonstrations of RL come from applying them to board games and video games. The first Reinforcement learning system to impress the global AI community want to learn the outplay humans in different Atari games when only given as input the images on screen and the scores received by playing the game.

The Deepmind and the AI research lab “OpenAI” have released systems for playing the video games Starcraft and DOTA 2 that can defeat the top human players around the world. These type of games are challenging because they require strategic thinking, resource management, and control and coordination of multiple entities within the game.