What is the machine learning technique that develops a policy to maximize a long-term or cumulative reward through trial and error?

What is the machine learning technique that develops a policy to maximize a long-term or cumulative reward through trial and error?

• A. Reinforcement Learning
• B. Supervised Learning
• C. Unsupervised Learning
• D. Deep Learning

Answer: (A)

Reinforcement learning is the approach where an agent interacts with an environment, choosing actions that lead to new states and rewards. The goal is to learn a policy—a way to map states to actions—that maximizes the expected cumulative reward over time. Because rewards come from sequences of actions, the agent must balance exploring new actions and exploiting known good ones, which is trial and error. This long-term focus on maximizing future returns sets reinforcement learning apart from supervised learning, which relies on labeled examples, and unsupervised learning, which seeks structure without rewards. Deep learning can be used within reinforcement learning to approximate policies or value functions, but the essential idea is learning from interaction to maximize long-term rewards.

Reinforcement learning is the approach where an agent interacts with an environment, choosing actions that lead to new states and rewards. The goal is to learn a policy—a way to map states to actions—that maximizes the expected cumulative reward over time. Because rewards come from sequences of actions, the agent must balance exploring new actions and exploiting known good ones, which is trial and error. This long-term focus on maximizing future returns sets reinforcement learning apart from supervised learning, which relies on labeled examples, and unsupervised learning, which seeks structure without rewards. Deep learning can be used within reinforcement learning to approximate policies or value functions, but the essential idea is learning from interaction to maximize long-term rewards.