Java Deep Learning Projects

Neural Q-learning

Most reinforcement learning algorithms boil down to just three main steps: infer, do, and learn. During the first step, the algorithm selects the best action a in a given state s using the knowledge it has so far. Next, it performs an action to find the reward r as well as the next state s'.

Then it improves its understanding of the world using the newly acquired knowledge (s, r, a, s'). These steps can be formulated even better using QLearning algorithms, which is more or less at the core of Deep Reinforcement Learning.