Reinforcement Learning
A type of machine learning where an agent learns to make decisions by taking actions in an environment and receiving rewards or penalties. The agent aims to maximize cumulative reward over time through trial and error.
Why It Matters
RL powers game-playing AI, robotics, autonomous systems, and recommendation engines. It is also central to aligning LLMs with human preferences through RLHF.
Example
DeepMind's AlphaGo learning to play Go by playing millions of games against itself, eventually defeating the world champion.
Think of it like...
Like training a dog with treats — the dog tries different behaviors, gets rewarded for good ones, and gradually learns which actions lead to the best outcomes.
Related Terms
RLHF
Reinforcement Learning from Human Feedback — a technique used to align language models with human preferences. Human raters rank model outputs, and this feedback trains a reward model that guides further training.
Exploration vs Exploitation
The fundamental tradeoff in reinforcement learning between trying new actions (exploration) to discover potentially better strategies and using known good actions (exploitation) to maximize current reward.