Reinforcement Learning
Definition
A type of machine learning where an agent learns to make decisions by taking actions in an environment and receiving rewards or penalties as feedback.
Reinforcement Learning (RL) is inspired by behavioral psychology and the way humans learn through trial and error. An agent interacts with an environment, observes states, takes actions, and receives rewards. The goal is to learn a policy that maximizes cumulative reward over time. Key algorithms include Q-learning, policy gradient methods, and actor-critic approaches. RL achieved major milestones including AlphaGo defeating the world champion at Go and training robotic hands to solve Rubik's cubes. RL from Human Feedback (RLHF) has become a critical technique for aligning large language models with human preferences.
Related Terms
Machine Learning
A subset of AI where systems learn patterns from data and improve their performance over time withou...
RLHF (Reinforcement Learning from Human Feedback)
A training technique where a language model is aligned with human preferences by training a reward m...
AI Agent
An AI system that can autonomously plan, make decisions, and take actions to accomplish goals, often...