Main Content

Reinforcement Learning Using Deep Neural Networks

Train deep neural network agents by interacting with an unknown dynamic environment

Reinforcement learning is a goal-directed computational approach where an agent learns to perform a task by interacting with an unknown dynamic environment. During training, the learning algorithm updates the agent policy parameters. The goal of the learning algorithm is to find an optimal policy that maximizes the long-term reward received during the task.

Depending on the type of agent, the policy is represented by one or more policy and value function representations. You can implement these representations using deep neural networks. You can then train these networks using Reinforcement Learning Toolbox™ software.

For more information, see Reinforcement Learning Using Deep Neural Networks.

Topics

Reinforcement Learning Using Deep Neural Networks

Reinforcement learning is a goal-directed computational approach where a computer learns to perform a task by interacting with an unknown dynamic environment.

Create Simulink Environment and Train Agent

Train a controller using reinforcement learning with a plant modeled in Simulink® as the training environment.

Create Agent Using Deep Network Designer and Train Using Image Observations

Create a reinforcement learning agent using the Deep Network Designer app from the Deep Learning Toolbox™.

Train DDPG Agent to Swing Up and Balance Pendulum with Image Observation

Train a reinforcement learning agent using an image-based observation signal.

Train DQN Agent for Lane Keeping Assist Using Parallel Computing

Train a reinforcement learning agent for a lane keeping assist application.

Imitate MPC Controller for Lane Keeping Assist

Train a deep neural network to imitate the behavior of a model predictive controller.

Featured Examples