MORAIDICTIONNAIRE IA
Fondamentaux

Reinforcement Learning (RL)

An AI that learns by trial and error, guided by rewards — much like training an animal.

Picture teaching a child to ride a bike: they try, fall, adjust, and each small success brings them closer to balance. Reinforcement Learning (RL) rests on exactly this idea: an agent learns to act within an environment by maximizing the rewards it receives, through repeated trial and error. Unlike supervised learning, no one hands it the "right answer" — it discovers that answer through experience.

The agent-environment loop

At each step, the agent observes a state ($s$), picks an action ($a$) according to its policy ($\pi$), and the environment returns a reward ($r$) and a new state. The goal is to maximize cumulative reward, weighted by a discount factor $\gamma \in [0,1]$ that favors the present over the distant future:

$$G_t = \sum_{k=0}^{\infty} \gamma^{k} \, r_{t+k+1}$$

The central challenge is the exploration / exploitation trade-off: should the agent exploit what it already knows, or explore to discover something better?

RL vs other paradigms

Paradigm Learning signal Example
Supervised Provided labels Classifying images
Unsupervised No target Clustering data
Reinforcement Delayed rewards Playing chess

Applications

RL doesn't learn what to answer, but how to behave in order to reach a goal.

Explore the full AI dictionary →