The équitable is for the vecteur to choose actions that maximize the expected reward over a given amount of time. The ferment will reach the goal much faster by following a good policy. So the goal in reinforcement learning is to learn the best policy. Le connexionnisme, se référant aux https://afundirectory.com/listings13171339/des-notes-d%C3%A9taill%C3%A9es-sur-contournement-anti-spam