In reinforcement learning methods, a trained agent interacts with a specific environment and takes actions based upon the current state of that environment.
The working of reinforcement learning is as follows −
Supervised learning methods, as we know, take both training data and its associated output during the training process. But the unsupervised learning methods do not require any labels or responses along with the training data and they learn patterns and relationships from the given raw data. Whereas in reinforcement learning methods the agent interacts with a specific environment in discrete steps.
If we talk about the output, supervised learning methods prediction is based on a class type and unsupervised learning methods discover underlying patterns but in reinforcement learning methods, there is a reward and action system in which the learning agent works.