ABSTRACT

Q-Learning is a Reinforcement Learning technique that works by learning an action-value function that gives the expected utility of taking a given action in a given state and following a fixed policy thereafter. One of the strengths of Q-Learning is that it is able to compare the expected utility of the available actions without requiring a model of the environment. Reinforcement Learning is an approach where the agent needs no teacher to learn how to solve a problem. The only signal used by the agent to learn from his actions in reinforcement environment is the so called reward, a number which tells the agent if his last action was good (or) not. Q-Learning is a recent form of Reinforcement Learning algorithm that does not need a model of its environment and can be used on-line. This paper discusses about the different strategies of Q-Learning algorithms and reward function.