You can build policy and value function representations for reinforcement learning applications using deep neural networks. You can then train these networks using Reinforcement Learning Toolbox™ software. For more information, see What Is Reinforcement Learning? (Reinforcement Learning Toolbox), Create Policy and Value Function Representations (Reinforcement Learning Toolbox), and Train Reinforcement Learning Agents (Reinforcement Learning Toolbox).
Train a controller using reinforcement learning with a plant modeled in Simulink® as the training environment.
Create a reinforcement learning agent using the Deep Network Designer app from the Deep Learning Toolbox™.
Train a reinforcement learning agent using an image-based observation signal.
Train a reinforcement learning agent for a lane keeping assist application.