Unity Examples

Here are the Unity examples that will be used in the course.

Pong

example-unity

Traing the agent to play the classic Pong game! You can either train it by show it how to play using supervised learning or let it play with itself using reinforcement learning. Read More ›

Pole

example-unity

Train a agent to balance a pole above its pivot by applying a torque, with either visual/vector observation. Read More ›

Maze

example-unity

Train a agent to go through a basic maze, with either visual/vector observation. Read More ›

Marathon Environment from Unity ML-Agents

example-unity

Training the Unity ml-agent's marathon environment. Read More ›

Intelligent Pool

example-unity

An example of playing the billiard using sampling based method, and how to combine it with supervised learning. Read More ›

Grid World

example-unity

A basic example where the AI is trained to reach to the destination and avoid the obstacle in a grid world. Read More ›

2D Plane - GAN

example-unity

Using Generative Adversarial Network(GAN) to generate data of multimodal guassian distribution on a 2D plane. Read More ›

Calamachine Union

example-unity

Calamachine Union! An actual game that uses reinforcement learning. The gameplay is to design and train your agent to play a platformer game! Read More ›

Banana Collectors

example-unity

A copy of the Unity ML-Agents' Banana Collector environment. The agents are trained to collect bananas, shoot at each other and avoid the bad bananas. Discrete action branching is used in this example. Read More ›

3D Ball

example-unity

A basic example where the AI is trained to balance a ball on a plate using both PPO and Neural Evolution Algorithm. The environment is a copy of the Unity ML-Agents' 3DBall environment. Read More ›