Behaviors in games---and in the real world---are often difficult to program explicitly. Reinforcement learning (RL) has shown success in learning behaviors based on a simple defined reward function that incentivises correct behavior.
Unity ML-Agents toolkit enables Unity developers to train reinforcement learning models to control behaviors within their games. Once these models are trained, they can be integrated across platforms into a game build via the Unity Inference Engine.
Furthermore, by enabling communication between a Unity build and Python code, ML-Agents enables RL researchers to use Unity games as training environments.