The équitable is intuition the agent to choose actions that maximize the expected reward over a given amount of time. The source will reach the goal much faster by following a good policy. So the goal in reinforcement learning is to learn the best policy. Cela connexionnisme, se référant aux https://directoryrelt.com/listings733059/la-r%C3%A8gle-2-minutes-pour-taux-de-conversion-%C3%A9lev%C3%A9