Reinforcement Learning

It is a feedback-based process, in which an AI agent (A software component) automatically explores its surroundings by hitting & trial, taking action, learning from experiences, and improving its performance. Agent gets rewarded for each good action and get punished for each bad action; hence the goal of reinforcement learning agent is to maximize the rewards.

In reinforcement learning, there is no labeled data like supervised learning, and agents learn from their experiences only. We use reinforcement learning much in robotics.

So reinforcement learning applied to automate mario game will look like-

enter image description here

Previous Index Next

End-to-End ML Project- Beginner friendly

Reinforcement Learning

XP

Loading comments...