What is Q-learning?

Q-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. Specifically, Q-learning seeks to learn a policy that tells an agent what action to take under what circumstances. It does not require a model of the environment (and so is 'model-free'), and it can handle problems with stochastic transitions and rewards without requiring adaptations. For any finite Markov decision process (MDP), Q-learning finds an optimal policy in the sense that it maximizes the expected value of the total reward over all successive steps, given the starting state. Q-learning is commonly used in robotics, game playing, and resource management.