← Library · Core concept
Reinforcement Learning
Reinforcement learning is a paradigm where an agent learns to make decisions by performing actions in an environment to maximize a cumulative reward. It learns through trial and error, getting positive or negative feedback (rewards or penalties) for its actions. This process helps the agent discover optimal strategies without explicitly being told what to do.
In plain terms
It's like teaching a dog tricks using treats as rewards and scolding as penalties, where the dog figures out which actions lead to the most treats.
Why it matters
It's crucial for training AI in sequential decision-making tasks, from robotics to game-playing and personalized recommendations.
Learn one new AI thing every day.
Daily Deck sends you seven plain-English cards like this every morning. Free.
Start free