Made from servo motors and tree branches, these robots were trained to successfully walk across the floor. Read the paper. (The project was undertaken by Preferred Networks of Japan, which also made this cool website called Paintschainer that colors black and white images using AI.)
The robots were trained with "deep reinforcement learning" (DRL). Here's how VentureBeat defines DRL:
Unlike supervised machine learning, which trains models based on known-correct answers, in reinforcement learning, researchers train the model by having an agent interact with an environment. When the agent's actions produce desired results, it gets positive feedback. For example, the agent gets a reward for scoring a point or winning a game. Put simply, researchers reinforce the agent's good behaviors.