Reinforcement learning

In reinforcement learning the agent has the ability to interact with the environment and find a better output. For this, it follows hit and trail formulae. This learning is used when there is no proper way to perform a task, but model needs to follow some strict rules to perform its duty. In this type of learning no labels are required. It has two types: one is positive and the other is negative. A survey on reinforcement learning was done by Kaelbling et al. (1996). Working model of reinforcement learning is shown in Figure 1X.5.