Differences

#1

Static (supervised/unsupervised) Vs.Dynamic (RL)

• Static: The goal of supervised and unsupervised learning is to search for and learn about patterns in training data, which is quite static.
• Dynamic: RL is about developing a policy that tells an agent which action to choose at each step — making it dynamic.

#2

No Explicit Right Answer in RL

• In supervised learning, the right answer is given by the training data.
• In Reinforcement Learning, the right answer is not explicitly given;  instead, the agent needs to learn by trial and error. The only reference is the reward it gets after taking an action, which tells the agent when it is making progress or when it has failed.

#3

RL Requires Exploration while supervised/unsupervised do not

• A Reinforcement Learning agent needs to find the right balance between exploring the environment, looking for new ways to get rewards, and exploiting the reward sources it has already discovered.
• Supervised and unsupervised learning systems take the answer directly from training data without having to explore other answers.

#4

RL is a Multiple-Decision Process while supervised learning is a single-decision process

• Reinforcement Learning is a multiple-decision process: it forms a decision-making chain through the time required to finish a specific job.
• Supervised learning is a single-decision process: one instance, one prediction.