Main Content

Reinforcement Learning

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

Reinforcement learning is a goal-directed computational learning 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 expected cumulative discounted long-term reward received during the task.

This learning approach enables the agent to make a series of decisions to maximize the cumulative reward for a task without human intervention and without being explicitly programmed to achieve a goal. You can create and train reinforcement learning agents using Reinforcement Learning Toolbox™ software.

For more information, see What Is Reinforcement Learning? (Reinforcement Learning Toolbox).

Topics

Featured Examples