This Video Of Two AI Cars Fighting Will Give You An Idea Of How Machines Think

Sebastian Schuchmann, a machine learning developer, has created two neural networks recently. When they are first made, they were like brothers. They learned and developed together in a strange world with just the other for company. However, Schuchmann then made them fought with each other to amuse his YouTube followers.

The two networks are represented as a green jeep and a police cruiser competing in a video game-like world. In Unity, there is a machine learning framework namely ML-Agents and Schuchmann makes use of it for most of his work. It has algorithms such as PPO, which OpenAI also uses. he also shared that he was moving more of his training to the cloud to speed up the process. However, there will always be a cost for everything.

The two neural networks are created in a way that they leverage reinforcement learning for completing different tasks. So in the video, the police car must find a way to stop the other vehicle from crossing the white line. If it fails, there will be a punishment; if it succeeds, it will get rewarded. The jeep must do the same thing to the police car and is under the system of reward and punishment too.

The performance is not exactly impressive, but it gives us an initial idea of the way reinforcement learning works. Machines like these learn by making use of brute force. Early in the video, the two cars did not do much, but later; they joined the game.

If they get enough time, we might have the chance to see more complicated tactics perform by these networks as they try to complete the assigned tasks. Many experts in this field fear that someday, this kind of learning may result in a doomsday for us.

For now, the video is a cool example of how machines think: