Founder, author, speaker

Reinforcement learning (RL) is an area of machine learning inspired by behavioral psychology. The concept of reinforcement learning is based on cumulative rewards or penalties for the actions that are taken by an agent in a dynamic environment.

Think about a young dog growing up. The dog is the agent in an environment that is our home. When we want the dog to sit, we usually say, “Sit.” The dog doesn’t understand English, so we might nudge it by lightly pushing down on its hindquarters.

After it sits, we pet the dog or give it a treat. This process will need to be repeated several times, and we would have positively reinforced the idea of sitting. The trigger in the environment is saying “Sit”; the behavior learned is sitting; and the reward is treats.

Where supervised learning uses labeled data to make predictions and classifications, and unsupervised learning uses unlabeled data to find clusters and trends, RL uses feedback from actions performed to learn what actions are most beneficial in different scenarios toward a goal.

Learn more about reinforcement learning in Grokking AI Algorithms with Manning Publications:, consider following me - @RishalHurbans, or join my mailing list for infrequent knowledge drops:

You’ve successfully subscribed to Rishal Hurbans
Welcome back! You’ve successfully signed in.
Great! You’ve successfully signed up.
Success! Your email is updated.
Your link has expired
Success! Check your email for magic link to sign-in.