Reinforcement Learning
A paradigm of machine learning where an agent learns to make sequential decisions in an environment by performing actions and receiving numerical rewards.
Think of It Like This
Like training a dog by giving it a treat when it successfully fetches a ball, and ignoring it when it completely misses the mark.
Unlike supervised learning which relies on static labeled datasets, RL models discover optimal behaviors through trial and error exploration. They aim to maximize the cumulative expected reward over time. This framework is responsible for conquering complex games like Go and Chess, and forms the backbone of aligning modern LLMs.